From ff861b6e23d69ee76f6176b73980b11878fbd96e Mon Sep 17 00:00:00 2001 From: Jonathan Burdge Date: Fri, 9 Oct 2026 11:15:22 +0300 Subject: [PATCH 1/2] Refresh LUMI exports and add merge3 checkpoint results --- README.md | 2 +- results/README.md | 9 + ..._merge3_116k_120k.flag-evals-471.tasks.csv | 2124 +++++++++ ...nealC_120k_l0fix.flag-evals-471.tasks.csv} | 101 + ..._merge3_116k_120k.flag-evals-471.tasks.csv | 2124 +++++++++ ..._merge3_116k_120k.flag-evals-471.tasks.csv | 2124 +++++++++ ...=> v1anneal_120k.flag-evals-471.tasks.csv} | 101 + ..._merge3_116k_120k.flag-evals-471.tasks.csv | 2124 +++++++++ ...=> v2anneal_120k.flag-evals-471.tasks.csv} | 4145 +++++++++-------- ..._merge3_116k_120k.flag-evals-471.tasks.csv | 2124 +++++++++ 10 files changed, 12955 insertions(+), 2023 deletions(-) create mode 100644 results/v1annealCT_merge3_116k_120k.flag-evals-471.tasks.csv rename results/{v1annealC_120k_l0fixed.flag-evals-438.tasks.csv => v1annealC_120k_l0fix.flag-evals-471.tasks.csv} (95%) create mode 100644 results/v1annealC_merge3_116k_120k.flag-evals-471.tasks.csv create mode 100644 results/v1annealTT_merge3_116k_120k.flag-evals-471.tasks.csv rename results/{v1anneal_120k.flag-evals-438.tasks.csv => v1anneal_120k.flag-evals-471.tasks.csv} (95%) create mode 100644 results/v1anneal_merge3_116k_120k.flag-evals-471.tasks.csv rename results/{v2anneal_120k.flag-evals-438.tasks.csv => v2anneal_120k.flag-evals-471.tasks.csv} (50%) create mode 100644 results/v2anneal_merge3_116k_120k.flag-evals-471.tasks.csv diff --git a/README.md b/README.md index 5777281..9e427bd 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@ A standalone, offline dashboard for comparing model evaluation scores. Explore c **[Open the dashboard](https://openeurollm.github.io/quickdash/)** or **[try the fictional example](https://openeurollm.github.io/quickdash/demo.html)**. No installation is needed to use either page. -The main page opens with **v1annealC_120k_l0fix** as A and **v2anneal_120k** as B, using the exports in [results/](results/README.md). The earlier v1 run and synthetic comparisons remain selectable. The startup pair is configured in [results/default.yaml](results/default.yaml). The default strict matching excludes results whose few-shot settings differ from the catalogue; review **Warnings**, or explicitly select relaxed matching to include them. +The main page opens with **v1annealC_120k_l0fix** as A and **v2anneal_120k** as B, using the exports in [results/](results/README.md). Other shared checkpoints, including the merge3 models, and synthetic comparisons remain selectable. The startup pair is configured in [results/default.yaml](results/default.yaml). The default strict matching excludes results whose few-shot settings differ from the catalogue; review **Warnings**, or explicitly select relaxed matching to include them. ## Compare models diff --git a/results/README.md b/results/README.md index 741b285..e486d80 100644 --- a/results/README.md +++ b/results/README.md @@ -4,6 +4,15 @@ Add a CSV directly to this directory to make its models available on the [shared When this directory contains no CSVs, Pages shows the [sample dataset and synthetic comparisons](../examples/README.md). Adding the first shared CSV replaces the sample. Remove `default.yaml` as well when removing all shared CSVs, so stale model references do not prevent the fallback build. +The shared files are `flag-evals-471` exports retrieved on 2026-10-09 from +`/scratch/project_465002530/poppelko/flag-evals/results/` on LUMI. Each contains +2,123 measurement rows, including 101 rows for 33 `_cot` reasoning and `_cont` +code-continuation tasks. These protocol variants have distinct task identifiers; +their raw rows are available for inspection but are not selected by the shipped +scoring rules. Dedicated catalogue rules are needed before these new metrics can +contribute to composite scores. The exports retain their original metric values, +shot counts, checkpoint labels, and source metadata. + Choose the models shown on first opening the dashboard in [default.yaml](default.yaml): ```yaml diff --git a/results/v1annealCT_merge3_116k_120k.flag-evals-471.tasks.csv b/results/v1annealCT_merge3_116k_120k.flag-evals-471.tasks.csv new file mode 100644 index 0000000..e088d46 --- /dev/null +++ b/results/v1annealCT_merge3_116k_120k.flag-evals-471.tasks.csv @@ -0,0 +1,2124 @@ +checkpoint,task,n_shot,harness,backend,is_group,metric,filter,value,stderr,n_samples,results_file,result_time,n_files +v1annealCT_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,accuracy_avg,,0.0,0.0,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8dc9b1eb22/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-05.314107.json,1791483540.7624295,1 +v1annealCT_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,solved_avg,,0.0,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8dc9b1eb22/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-05.314107.json,1791483540.7624295,1 +v1annealCT_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,accuracy_avg,,0.06666666666666667,0.0,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fcea11cc1b/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-32-41.497934.json,1791484357.2805831,1 +v1annealCT_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,solved_avg,,2.0,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fcea11cc1b/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-32-41.497934.json,1791484357.2805831,1 +v1annealCT_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,accuracy_avg,,0.12,0.0031622776601683785,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/50c2a22588/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-01-53.163169.json,1791482506.095553,1 +v1annealCT_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,solved_avg,,4.8,,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/50c2a22588/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-01-53.163169.json,1791482506.095553,1 +v1annealCT_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,accuracy_avg,,0.24915824915824913,0.016205981008073692,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/525f1755ac/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-12-50.963355.json,1791483166.451456,1 +v1annealCT_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,solved_avg,,49.333333333333336,,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/525f1755ac/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-12-50.963355.json,1791483166.451456,1 +v1annealCT_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,python_pass@1,,0.4634146341463415,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/42c2a35291/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T17-39-11.667104.json,1791481148.0684938,1 +v1annealCT_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,sh_pass@1,,0.4177215189873418,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/42c2a35291/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T17-39-11.667104.json,1791481148.0684938,1 +v1annealCT_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,accuracy_avg,,0.32912621359223304,0.005198180713336242,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1b57c0d711/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-27-32.811027.json,1791484048.4280722,1 +v1annealCT_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,solved_avg,,169.5,,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1b57c0d711/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-27-32.811027.json,1791484048.4280722,1 +v1annealCT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_avg,,0.10730593607305937,0.0010618930591063083,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc239fab22/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-30-03.654771.json,1791484199.7593224,1 +v1annealCT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_easy_avg,,0.27014652014652013,0.0038635573461042088,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc239fab22/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-30-03.654771.json,1791484199.7593224,1 +v1annealCT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_hard_avg,,0.016260162601626018,0.0,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc239fab22/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-30-03.654771.json,1791484199.7593224,1 +v1annealCT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_medium_avg,,0.017799352750809058,0.0010233908285334557,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc239fab22/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-30-03.654771.json,1791484199.7593224,1 +v1annealCT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,solved_avg,,54.833333333333336,,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc239fab22/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-30-03.654771.json,1791484199.7593224,1 +v1annealCT_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,accuracy,,0.458,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2165269287/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-05-09.921409.json,1791482705.5091403,1 +v1annealCT_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,num_solved,,229,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2165269287/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealCT_merge3_116k_120k/results_2026-10-08T18-05-09.921409.json,1791482705.5091403,1 +v1annealCT_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc,none,0.2782608695652174,0.029614094221633747,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/453c8c74a2_2026-10-08T17-32-11.004975.json,1791480549.8347244,1 +v1annealCT_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc_norm,none,0.2391304347826087,0.028187385293933997,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/453c8c74a2_2026-10-08T17-32-11.004975.json,1791480549.8347244,1 +v1annealCT_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc,none,0.6254266211604096,0.014144193471893432,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ed6629013f_2026-10-08T17-39-28.466825.json,1791480976.6527884,1 +v1annealCT_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc_norm,none,0.6348122866894198,0.014070265519268777,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ed6629013f_2026-10-08T17-39-28.466825.json,1791480976.6527884,1 +v1annealCT_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc,none,0.6262798634812287,0.014137708601759029,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/384e7ff354_2026-10-08T17-35-33.255069.json,1791480701.366477,1 +v1annealCT_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc_norm,none,0.6569965870307167,0.0138724232237182,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/384e7ff354_2026-10-08T17-35-33.255069.json,1791480701.366477,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc,none,0.552901023890785,0.01452938016052677,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f9d0e98910_2026-10-08T18-01-19.408701.json,1791482232.22984,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc_norm,none,0.5656996587030717,0.014484703048857371,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f9d0e98910_2026-10-08T18-01-19.408701.json,1791482232.22984,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc,none,0.5409556313993175,0.01456229107360112,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/71ba9f6928_2026-10-08T17-35-30.695201.json,1791480692.9071681,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc_norm,none,0.5665529010238908,0.014481376224558896,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/71ba9f6928_2026-10-08T17-35-30.695201.json,1791480692.9071681,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc,none,0.5426621160409556,0.014558106543923992,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/72f8bcb846_2026-10-08T17-40-14.103665.json,1791480977.6951134,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc_norm,none,0.5827645051194539,0.014409825518403108,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/72f8bcb846_2026-10-08T17-40-14.103665.json,1791480977.6951134,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc,none,0.515358361774744,0.014604496129394757,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/382b9f2cd2_2026-10-08T17-38-07.878759.json,1791480849.074178,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc_norm,none,0.5622866894197952,0.01449757388110822,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/382b9f2cd2_2026-10-08T17-38-07.878759.json,1791480849.074178,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc,none,0.5418088737201365,0.014560220308714553,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cff4e1ea19_2026-10-08T18-08-39.089749.json,1791482659.238276,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc_norm,none,0.568259385665529,0.014474591427196025,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cff4e1ea19_2026-10-08T18-08-39.089749.json,1791482659.238276,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc,none,0.5665529010238908,0.014481376224558896,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/80e83bbfc7_2026-10-08T17-44-51.017298.json,1791481250.3728008,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc_norm,none,0.60580204778157,0.014280522667467148,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/80e83bbfc7_2026-10-08T17-44-51.017298.json,1791481250.3728008,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc,none,0.5,0.014611390804670088,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/44276096cd_2026-10-08T17-35-28.450929.json,1791480695.0351512,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc_norm,none,0.53839590443686,0.014568245550296302,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/44276096cd_2026-10-08T17-35-28.450929.json,1791480695.0351512,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc,none,0.4872013651877133,0.014606603181012609,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7ca8b75e67_2026-10-08T18-08-17.161390.json,1791482655.798017,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc_norm,none,0.5324232081911263,0.014580637569995414,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7ca8b75e67_2026-10-08T18-08-17.161390.json,1791482655.798017,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc,none,0.5699658703071673,0.01446763155913799,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/016899ab0a_2026-10-08T18-03-52.206791.json,1791482375.3243334,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc_norm,none,0.6032423208191127,0.014296513020180628,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/016899ab0a_2026-10-08T18-03-52.206791.json,1791482375.3243334,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc,none,0.49402730375426623,0.014610348300255798,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/569ae18890_2026-10-08T18-01-22.001650.json,1791482233.3606246,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc_norm,none,0.5409556313993175,0.01456229107360112,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/569ae18890_2026-10-08T18-01-22.001650.json,1791482233.3606246,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc,none,0.49658703071672355,0.014611050403244159,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bc3ddb6eaf_2026-10-08T17-40-26.314458.json,1791480980.3323758,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc_norm,none,0.537542662116041,0.014570144495075503,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bc3ddb6eaf_2026-10-08T17-40-26.314458.json,1791480980.3323758,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc,none,0.5486348122866894,0.014542104569955378,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/623010ec1b_2026-10-08T17-40-12.903994.json,1791480972.6651056,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc_norm,none,0.5938566552901023,0.014351656690097877,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/623010ec1b_2026-10-08T17-40-12.903994.json,1791480972.6651056,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc,none,0.5204778156996587,0.01459913135303498,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d0da6eb3b3_2026-10-08T17-44-42.084407.json,1791481250.6332967,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc_norm,none,0.5460750853242321,0.014549221105171829,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d0da6eb3b3_2026-10-08T17-44-42.084407.json,1791481250.6332967,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc,none,0.514505119453925,0.014605241081370146,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/01d9828da1_2026-10-08T17-43-02.143975.json,1791481123.3307989,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc_norm,none,0.5366894197952219,0.014572000527756918,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/01d9828da1_2026-10-08T17-43-02.143975.json,1791481123.3307989,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc,none,0.537542662116041,0.014570144495075503,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/710527f908_2026-10-08T17-35-31.617311.json,1791480694.5813985,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc_norm,none,0.5810580204778157,0.01441810695363902,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/710527f908_2026-10-08T17-35-31.617311.json,1791480694.5813985,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc,none,0.5520477815699659,0.014532011498211617,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5046ca906d_2026-10-08T17-40-20.863839.json,1791480975.9513514,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc_norm,none,0.568259385665529,0.014474591427196025,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5046ca906d_2026-10-08T17-40-20.863839.json,1791480975.9513514,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc,none,0.53839590443686,0.014568245550296302,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/53d510da98_2026-10-08T18-12-37.644153.json,1791482924.779053,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc_norm,none,0.5588737201365188,0.014509747749064824,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/53d510da98_2026-10-08T18-12-37.644153.json,1791482924.779053,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc,none,0.560580204778157,0.014503747823580139,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/938cae0da3_2026-10-08T17-44-49.804772.json,1791481250.5143766,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc_norm,none,0.6049488054607508,0.014285898292938231,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/938cae0da3_2026-10-08T17-44-49.804772.json,1791481250.5143766,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc,none,0.552901023890785,0.01452938016052677,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bce86222c2_2026-10-08T18-10-51.350804.json,1791482802.9886694,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc_norm,none,0.5810580204778157,0.01441810695363902,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bce86222c2_2026-10-08T18-10-51.350804.json,1791482802.9886694,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc,none,0.5341296928327645,0.014577311315231023,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/eb338cd5b2_2026-10-08T18-01-15.454953.json,1791482235.0847764,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc_norm,none,0.5802047781569966,0.014422181226303012,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/eb338cd5b2_2026-10-08T18-01-15.454953.json,1791482235.0847764,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc,none,0.5324232081911263,0.014580637569995414,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/31bcccb683_2026-10-08T18-10-36.994056.json,1791482797.5182512,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc_norm,none,0.5631399317406144,0.014494421584256512,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/31bcccb683_2026-10-08T18-10-36.994056.json,1791482797.5182512,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc,none,0.53839590443686,0.014568245550296302,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8740f6139d_2026-10-08T18-10-40.058918.json,1791482800.562231,1 +v1annealCT_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc_norm,none,0.5844709897610921,0.014401366641216409,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8740f6139d_2026-10-08T18-10-40.058918.json,1791482800.562231,1 +v1annealCT_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc,none,0.8665824915824916,0.006977174118514789,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d595556f81_2026-10-08T18-08-16.454297.json,1791482666.9429688,1 +v1annealCT_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc_norm,none,0.8733164983164983,0.006825179144275699,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d595556f81_2026-10-08T18-08-16.454297.json,1791482666.9429688,1 +v1annealCT_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/999c8c1d43_2026-10-08T17-34-57.363832.json,1791480694.8125637,1 +v1annealCT_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc_norm,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/999c8c1d43_2026-10-08T17-34-57.363832.json,1791480694.8125637,1 +v1annealCT_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7d745d3433_2026-10-08T17-44-11.992450.json,1791481256.3511145,1 +v1annealCT_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc_norm,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7d745d3433_2026-10-08T17-44-11.992450.json,1791481256.3511145,1 +v1annealCT_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8e300845f8_2026-10-08T17-44-07.783458.json,1791481255.3611171,1 +v1annealCT_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc_norm,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8e300845f8_2026-10-08T17-44-07.783458.json,1791481255.3611171,1 +v1annealCT_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc,none,0.91,0.009544696096877968,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/61fc87f06e_2026-10-08T17-53-19.857664.json,1791481808.6436436,1 +v1annealCT_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc_norm,none,0.91,0.009544696096877968,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/61fc87f06e_2026-10-08T17-53-19.857664.json,1791481808.6436436,1 +v1annealCT_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f012ddbee2_2026-10-08T17-50-54.418225.json,1791481670.1880648,1 +v1annealCT_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc_norm,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f012ddbee2_2026-10-08T17-50-54.418225.json,1791481670.1880648,1 +v1annealCT_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b0cbd648fa_2026-10-08T18-05-08.656397.json,1791482512.987721,1 +v1annealCT_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc_norm,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b0cbd648fa_2026-10-08T18-05-08.656397.json,1791482512.987721,1 +v1annealCT_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c0b7b7edf1_2026-10-08T18-00-29.540709.json,1791482237.5703013,1 +v1annealCT_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc_norm,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c0b7b7edf1_2026-10-08T18-00-29.540709.json,1791482237.5703013,1 +v1annealCT_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ef0d85d2fb_2026-10-08T17-41-43.180042.json,1791481113.40477,1 +v1annealCT_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc_norm,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ef0d85d2fb_2026-10-08T17-41-43.180042.json,1791481113.40477,1 +v1annealCT_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc,none,0.9144444444444444,0.009328738621020953,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/724c8a8196_2026-10-08T17-53-33.731748.json,1791481817.1152532,1 +v1annealCT_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc_norm,none,0.9144444444444444,0.009328738621020953,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/724c8a8196_2026-10-08T17-53-33.731748.json,1791481817.1152532,1 +v1annealCT_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc,none,0.89,0.010435457652553744,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/18cdc4cab9_2026-10-08T17-44-04.105062.json,1791481255.3096702,1 +v1annealCT_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc_norm,none,0.89,0.010435457652553744,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/18cdc4cab9_2026-10-08T17-44-04.105062.json,1791481255.3096702,1 +v1annealCT_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc,none,0.89,0.010435457652553744,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f3548b786d_2026-10-08T18-00-23.720565.json,1791482235.9601233,1 +v1annealCT_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc_norm,none,0.89,0.010435457652553744,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f3548b786d_2026-10-08T18-00-23.720565.json,1791482235.9601233,1 +v1annealCT_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a032955bcf_2026-10-08T18-14-27.421008.json,1791483081.4898686,1 +v1annealCT_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc_norm,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a032955bcf_2026-10-08T18-14-27.421008.json,1791483081.4898686,1 +v1annealCT_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc,none,0.89,0.010435457652553744,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e50ebd56c_2026-10-08T17-41-46.612206.json,1791481115.033747,1 +v1annealCT_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc_norm,none,0.89,0.010435457652553744,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e50ebd56c_2026-10-08T17-41-46.612206.json,1791481115.033747,1 +v1annealCT_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/27fd81047f_2026-10-08T17-37-09.339243.json,1791480848.9832006,1 +v1annealCT_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc_norm,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/27fd81047f_2026-10-08T17-37-09.339243.json,1791480848.9832006,1 +v1annealCT_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7787e85a7c_2026-10-08T17-57-49.094989.json,1791482086.9415088,1 +v1annealCT_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc_norm,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7787e85a7c_2026-10-08T17-57-49.094989.json,1791482086.9415088,1 +v1annealCT_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc,none,0.8877777777777778,0.010527172059500687,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c1ecc79a26_2026-10-08T17-37-19.195201.json,1791480848.7642078,1 +v1annealCT_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc_norm,none,0.8877777777777778,0.010527172059500687,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c1ecc79a26_2026-10-08T17-37-19.195201.json,1791480848.7642078,1 +v1annealCT_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c57c68ebf0_2026-10-08T17-41-41.369902.json,1791481116.1223395,1 +v1annealCT_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc_norm,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c57c68ebf0_2026-10-08T17-41-41.369902.json,1791481116.1223395,1 +v1annealCT_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc,none,0.8833333333333333,0.010706705536407178,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/41985d0ec7_2026-10-08T17-41-37.308008.json,1791481112.2512903,1 +v1annealCT_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc_norm,none,0.8833333333333333,0.010706705536407178,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/41985d0ec7_2026-10-08T17-41-37.308008.json,1791481112.2512903,1 +v1annealCT_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc,none,0.8988888888888888,0.010054780672527,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f081ed0597_2026-10-08T17-32-28.717186.json,1791480553.343571,1 +v1annealCT_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc_norm,none,0.8988888888888888,0.010054780672527,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f081ed0597_2026-10-08T17-32-28.717186.json,1791480553.343571,1 +v1annealCT_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2633a7084a_2026-10-08T17-39-29.355072.json,1791480975.86379,1 +v1annealCT_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc_norm,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2633a7084a_2026-10-08T17-39-29.355072.json,1791480975.86379,1 +v1annealCT_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ea4211bb98_2026-10-08T17-41-39.450788.json,1791481112.7164357,1 +v1annealCT_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc_norm,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ea4211bb98_2026-10-08T17-41-39.450788.json,1791481112.7164357,1 +v1annealCT_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc,none,0.9022222222222223,0.009905969703297319,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b941b1ae73_2026-10-08T17-34-40.789582.json,1791480694.0297546,1 +v1annealCT_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc_norm,none,0.9022222222222223,0.009905969703297319,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b941b1ae73_2026-10-08T17-34-40.789582.json,1791480694.0297546,1 +v1annealCT_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5d2c3bdc90_2026-10-08T18-07-37.853223.json,1791482662.6164966,1 +v1annealCT_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc_norm,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5d2c3bdc90_2026-10-08T18-07-37.853223.json,1791482662.6164966,1 +v1annealCT_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/51bb52cadb_2026-10-08T17-50-55.938220.json,1791481666.7815518,1 +v1annealCT_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc_norm,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/51bb52cadb_2026-10-08T17-50-55.938220.json,1791481666.7815518,1 +v1annealCT_merge3_116k_120k,bigbench_cs_algorithms_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7825757575757576,0.01135781473012721,1320,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/44a932c981_2026-10-08T17-50-55.895105.json,1791481666.1947212,1 +v1annealCT_merge3_116k_120k,bigbench_dyck_languages_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.598,0.015512467135715078,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a083c1e592_2026-10-08T17-32-26.508470.json,1791480549.6062856,1 +v1annealCT_merge3_116k_120k,bigbench_language_identification_multiple_choice,10,lm-eval,vllm,,acc,none,0.2329,0.004227001981851376,10000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cf9693ca2a_2026-10-08T18-49-18.984358.json,1791481668.4056528,1 +v1annealCT_merge3_116k_120k,bigbench_operators_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.8523809523809524,0.024536630598841102,210,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9e0d601eba_2026-10-08T17-41-21.150479.json,1791481110.6855693,1 +v1annealCT_merge3_116k_120k,bigbench_qa_wikidata_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.722553023965356,0.0031409643524216227,20321,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9ccf7738a5_2026-10-08T18-06-59.823008.json,1791482521.1508222,1 +v1annealCT_merge3_116k_120k,bigbench_repeat_copy_logic_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.625,0.08695104295503155,32,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d07c41fbeb_2026-10-08T17-43-47.800230.json,1791481253.3954475,1 +v1annealCT_merge3_116k_120k,boolq,10,lm-eval,vllm,,acc,none,0.8721712538226299,0.0058399306324134976,3270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f0849e05a3_2026-10-08T17-37-28.975871.json,1791480698.6476355,1 +v1annealCT_merge3_116k_120k,commonsense_qa,10,lm-eval,vllm,,acc,none,0.8198198198198198,0.011003549459018392,1221,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d32f62a104_2026-10-08T18-03-07.020786.json,1791482374.4325674,1 +v1annealCT_merge3_116k_120k,copa,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/139368866f_2026-10-08T17-39-10.379914.json,1791480976.3486106,1 +v1annealCT_merge3_116k_120k,coqa,0,lm-eval,vllm,,em,none,0.6933333333333334,0.016710696683747247,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5cf7244f74_2026-10-08T17-50-52.685289.json,1791481665.512745,1 +v1annealCT_merge3_116k_120k,coqa,0,lm-eval,vllm,,f1,none,0.8220473307569858,0.011835088926912572,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5cf7244f74_2026-10-08T17-50-52.685289.json,1791481665.512745,1 +v1annealCT_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.040600394708825,0.0181962047807885,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c2bb77da37/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-32.957861.json,1791483813.852643,1 +v1annealCT_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7084250307173665,0.00395649296959055,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c2bb77da37/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-32.957861.json,1791483813.852643,1 +v1annealCT_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.26967799236989437,0.006187473448190001,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c2bb77da37/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-32.957861.json,1791483813.852643,1 +v1annealCT_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.12400559483497,0.012073263659594793,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c2bb77da37/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-32.957861.json,1791483813.852643,1 +v1annealCT_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.12191594148567,0.018315690447722494,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/98c3bc3621/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-07.457845.json,1791483488.378347,1 +v1annealCT_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7172902396000506,0.003755849404829494,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/98c3bc3621/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-07.457845.json,1791483488.378347,1 +v1annealCT_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28484793781731116,0.006435844139624857,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/98c3bc3621/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-07.457845.json,1791483488.378347,1 +v1annealCT_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.3265456609423,0.011557069155185238,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/98c3bc3621/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-07.457845.json,1791483488.378347,1 +v1annealCT_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.735038874476864,0.017704603753979063,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4a3488f0e0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-08.387433.json,1791483489.526628,1 +v1annealCT_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7047108292569649,0.003902190425830456,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4a3488f0e0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-08.387433.json,1791483489.526628,1 +v1annealCT_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.26493111516539924,0.006114654407354263,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4a3488f0e0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-08.387433.json,1791483489.526628,1 +v1annealCT_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.25849685203859,0.011939955773891437,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4a3488f0e0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-08.387433.json,1791483489.526628,1 +v1annealCT_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,49.55930224296611,0.020094769799643766,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5e6d5e9314/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-09.190742.json,1791483670.203027,1 +v1annealCT_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.737185438245528,0.004001162377406831,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5e6d5e9314/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-09.190742.json,1791483670.203027,1 +v1annealCT_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.32736925111894405,0.007121703522433332,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5e6d5e9314/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-09.190742.json,1791483670.203027,1 +v1annealCT_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.69478885474345,0.013076289608512471,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5e6d5e9314/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-09.190742.json,1791483670.203027,1 +v1annealCT_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.14761954179438,0.017952872589059827,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c392a29af6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-41.438278.json,1791482142.255646,1 +v1annealCT_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6931993565779383,0.003998930386806902,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c392a29af6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-41.438278.json,1791482142.255646,1 +v1annealCT_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.25851458147543943,0.006185984907474537,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c392a29af6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-41.438278.json,1791482142.255646,1 +v1annealCT_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.80895193017585,0.012453724018581622,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c392a29af6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-41.438278.json,1791482142.255646,1 +v1annealCT_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,52.087563560451024,0.019425781277187193,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/3228b248ba/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-19.036809.json,1791481939.898905,1 +v1annealCT_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7533263758257189,0.0038678909735798805,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/3228b248ba/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-19.036809.json,1791481939.898905,1 +v1annealCT_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.35311760737899883,0.006955487713826848,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/3228b248ba/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-19.036809.json,1791481939.898905,1 +v1annealCT_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.53157502723695,0.012857982176456766,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/3228b248ba/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-19.036809.json,1791481939.898905,1 +v1annealCT_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.78256218832777,0.01963242008691606,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/d644e3ff02/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-52.272501.json,1791482093.075304,1 +v1annealCT_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7209599500097901,0.003934499268331341,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/d644e3ff02/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-52.272501.json,1791482093.075304,1 +v1annealCT_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2978961489776746,0.006728868486304904,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/d644e3ff02/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-52.272501.json,1791482093.075304,1 +v1annealCT_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.59569454205638,0.012968629973974043,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/d644e3ff02/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-52.272501.json,1791482093.075304,1 +v1annealCT_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.29294053258529,0.01815906559146141,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c34e97d6ba/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-44.430503.json,1791483525.55706,1 +v1annealCT_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6623473435366416,0.004202275186629521,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c34e97d6ba/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-44.430503.json,1791483525.55706,1 +v1annealCT_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2243166264444023,0.0057491175290183315,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c34e97d6ba/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-44.430503.json,1791483525.55706,1 +v1annealCT_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.9794261830199,0.012920372465234307,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c34e97d6ba/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-44.430503.json,1791483525.55706,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu,none,34.10368315120772,0.015256300330261964,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c9b4a024b6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-25-03.899526.json,1791483904.738422,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6261166888908756,0.0037665484189696933,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c9b4a024b6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-25-03.899526.json,1791483904.738422,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17984204716608407,0.004740278198398951,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c9b4a024b6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-25-03.899526.json,1791483904.738422,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.113899762930956,0.0106571618804637,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c9b4a024b6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-25-03.899526.json,1791483904.738422,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu,none,32.18631319132008,0.01749508105452814,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a86bbc4110/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-23.824593.json,1791483684.647305,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5976458645577293,0.004464585641454272,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a86bbc4110/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-23.824593.json,1791483684.647305,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1636151594180165,0.00479002677567632,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a86bbc4110/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-23.824593.json,1791483684.647305,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.09780583911694,0.012409191177702634,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a86bbc4110/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-23.824593.json,1791483684.647305,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu,none,40.16605049241847,0.017984185835295267,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6a1e0ef73d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-58.871606.json,1791481979.705753,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.654695948697423,0.00405486768050808,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6a1e0ef73d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-58.871606.json,1791481979.705753,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.2210886418093549,0.005497343620245399,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6a1e0ef73d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-58.871606.json,1791481979.705753,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,63.975710195496404,0.012150051017579717,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6a1e0ef73d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-58.871606.json,1791481979.705753,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu,none,43.845830872902404,0.018051063571855118,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4e1026661e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-53.385388.json,1791483834.236249,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6738430874192578,0.004235233604910546,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4e1026661e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-53.385388.json,1791483834.236249,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.26886232419229467,0.006104370929415355,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4e1026661e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-53.385388.json,1791483834.236249,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.1317027490727,0.012879945629319826,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4e1026661e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-53.385388.json,1791483834.236249,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu,none,32.41270208265887,0.01969514315975954,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/126c683042/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-58.609194.json,1791482100.124443,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5898519202571669,0.004855897647053998,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/126c683042/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-58.609194.json,1791482100.124443,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16888826961351514,0.005628786002688564,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/126c683042/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-58.609194.json,1791482100.124443,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.70220799167102,0.014016121750171273,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/126c683042/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-58.609194.json,1791482100.124443,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu,none,48.31694572749192,0.019520513700967083,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/46327fc61f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-40.874236.json,1791482022.121752,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7103540849831083,0.004351190615889024,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/46327fc61f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-40.874236.json,1791482022.121752,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.31836810697741863,0.006993261851693967,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/46327fc61f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-40.874236.json,1791482022.121752,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.10788375101143,0.012514478647036295,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/46327fc61f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-40.874236.json,1791482022.121752,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu,none,39.97354786082259,0.021372183885621718,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/cc690d7e21/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-42.239496.json,1791483643.296874,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.651505759426718,0.004681867862528897,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/cc690d7e21/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-42.239496.json,1791483643.296874,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23609176808334026,0.006530079551601211,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/cc690d7e21/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-42.239496.json,1791483643.296874,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.59665081971596,0.013915240783922337,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/cc690d7e21/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-42.239496.json,1791483643.296874,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu,none,26.761018608666966,0.015458289702149705,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/20eaff9d5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-46.031756.json,1791482026.877865,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_1,none,0.5359885917370406,0.00445664773093881,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/20eaff9d5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-46.031756.json,1791482026.877865,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_4,none,0.12477079670714356,0.004198101225468478,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/20eaff9d5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-46.031756.json,1791482026.877865,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,chrf++,rescored,51.06519375570878,0.012702824137032293,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/20eaff9d5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-46.031756.json,1791482026.877865,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu,none,27.02028545261981,0.01915362727631311,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/278c95844e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-16.764933.json,1791483377.585082,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5529799027561412,0.005041764811738903,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/278c95844e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-16.764933.json,1791483377.585082,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12914943466901002,0.005379700784102109,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/278c95844e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-16.764933.json,1791483377.585082,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.92546484852987,0.013087409151576869,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/278c95844e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-16.764933.json,1791483377.585082,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu,none,18.748498023109136,0.016151337930166276,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/352430fb58/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-43.114889.json,1791481964.810552,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.4843328391757853,0.004681436703106091,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/352430fb58/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-43.114889.json,1791481964.810552,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.07219651590979279,0.0036820782646161156,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/352430fb58/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-43.114889.json,1791481964.810552,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,51.914583017573236,0.011532214627670255,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/352430fb58/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-43.114889.json,1791481964.810552,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu,none,25.144617147427827,0.019468224484359743,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/57042172dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-22-01.951996.json,1791483723.486106,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5218651105552251,0.00524906629508505,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/57042172dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-22-01.951996.json,1791483723.486106,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1171540170881657,0.005238374834113319,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/57042172dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-22-01.951996.json,1791483723.486106,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.05374308572143,0.013230915590702351,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/57042172dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-22-01.951996.json,1791483723.486106,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu,none,50.95311022715086,0.023415589421039412,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5496b7b347/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-00.704585.json,1791483542.166402,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7011403283964699,0.0049506958759982286,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5496b7b347/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-00.704585.json,1791483542.166402,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.36198919407627284,0.007996341234212155,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5496b7b347/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-00.704585.json,1791483542.166402,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.76344567292107,0.01547717726738413,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5496b7b347/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-00.704585.json,1791483542.166402,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu,none,31.642067135748793,0.01793776367501876,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/410e6285dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-53.769781.json,1791482035.121102,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5834267641282088,0.004498798235874811,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/410e6285dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-53.769781.json,1791482035.121102,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16754036207190512,0.005237701332574189,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/410e6285dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-53.769781.json,1791482035.121102,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.46394572866086,0.013248818208279329,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/410e6285dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-53.769781.json,1791482035.121102,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu,none,37.68233822130651,0.01625626708827988,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6a9a1dcc1c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-23.062427.json,1791481944.31248,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6421836970259469,0.0038046094876782017,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6a9a1dcc1c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-23.062427.json,1791481944.31248,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2136929485603439,0.005456892629516025,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6a9a1dcc1c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-23.062427.json,1791481944.31248,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.25488027092983,0.010828799239886961,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6a9a1dcc1c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-23.062427.json,1791481944.31248,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.637569874460638,0.018874850855436734,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ff752ed349/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-08.820829.json,1791482110.005315,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5762989654425895,0.004990928299666315,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ff752ed349/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-08.820829.json,1791482110.005315,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1635815603173095,0.005569244672561119,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ff752ed349/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-08.820829.json,1791482110.005315,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.23200544918129,0.01371887223591823,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ff752ed349/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-08.820829.json,1791482110.005315,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu,none,26.25265627693546,0.018826484176689466,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c77b80b99e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-42.217631.json,1791482023.065511,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5588909028135605,0.00450564559317943,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c77b80b99e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-42.217631.json,1791482023.065511,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11451030791360484,0.004640820003676436,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c77b80b99e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-42.217631.json,1791482023.065511,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.7835401623614,0.012401055620475096,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c77b80b99e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-42.217631.json,1791482023.065511,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu,none,28.76476950760304,0.018811117690015974,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c46a5a1174/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-53.088207.json,1791481973.881075,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5452088409852187,0.004894020858011048,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c46a5a1174/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-53.088207.json,1791481973.881075,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.14505219246769713,0.005570481854603191,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c46a5a1174/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-53.088207.json,1791481973.881075,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,53.15868699631535,0.013741274119270253,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c46a5a1174/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-53.088207.json,1791481973.881075,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu,none,32.52980477654372,0.014599709842772151,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e107d2d9ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-15.456378.json,1791481936.260376,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5954588935303365,0.003821142837543335,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e107d2d9ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-15.456378.json,1791481936.260376,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16339490152927666,0.004229406605068521,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e107d2d9ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-15.456378.json,1791481936.260376,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.083328936779154,0.010192792376394966,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e107d2d9ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-15.456378.json,1791481936.260376,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu,none,3.6318192785347034,0.00675280875016912,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e8fbb98a67/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-25-05.850543.json,1791483906.828965,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_1,none,0.21250892765560447,0.00395568124278949,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e8fbb98a67/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-25-05.850543.json,1791483906.828965,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_4,none,0.0061571844687646135,0.0008216498562128512,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e8fbb98a67/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-25-05.850543.json,1791483906.828965,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,chrf++,rescored,26.078701062262205,0.008749274666881773,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e8fbb98a67/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-25-05.850543.json,1791483906.828965,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu,none,27.31091042515959,0.01973751462374482,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/fe57e9d571/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-16.004282.json,1791483856.904365,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5492953364382747,0.005093994039688586,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/fe57e9d571/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-16.004282.json,1791483856.904365,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1296136933157426,0.005152933962997331,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/fe57e9d571/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-16.004282.json,1791483856.904365,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.163086742165945,0.013951853664877544,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/fe57e9d571/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-16.004282.json,1791483856.904365,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu,none,31.5545515107842,0.02047055771439549,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c35f4ce9d8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-19.400039.json,1791483860.278079,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5878828579350562,0.005216352550937248,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c35f4ce9d8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-19.400039.json,1791483860.278079,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16806246436631264,0.006144982723204608,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c35f4ce9d8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-19.400039.json,1791483860.278079,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.57209050194818,0.014921444928267585,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c35f4ce9d8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-19.400039.json,1791483860.278079,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu,none,35.865797785632914,0.01695807890573682,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/09b7a5ecea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-57.749682.json,1791483418.77898,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6284336262750465,0.003903527370308843,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/09b7a5ecea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-57.749682.json,1791483418.77898,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.19011988757237605,0.00511172001377909,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/09b7a5ecea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-57.749682.json,1791483418.77898,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,61.66532697599383,0.011606197870983123,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/09b7a5ecea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-57.749682.json,1791483418.77898,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu,none,40.32715358665018,0.020154952215852742,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/9918cfdef4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-56.842680.json,1791482037.956354,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6544764548290495,0.004577702568744855,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/9918cfdef4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-56.842680.json,1791482037.956354,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23776005149426097,0.006649822102595925,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/9918cfdef4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-56.842680.json,1791482037.956354,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.28437166508692,0.01326887946439097,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/9918cfdef4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-56.842680.json,1791482037.956354,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu,none,28.073740102388047,0.016821769566406578,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4b8fac80aa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-50-34.195453.json,1791481835.025904,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5758817598817104,0.004338416054112865,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4b8fac80aa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-50-34.195453.json,1791481835.025904,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1297014995537611,0.004613011432096656,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4b8fac80aa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-50-34.195453.json,1791481835.025904,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.8630004048163,0.011836133694057968,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4b8fac80aa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-50-34.195453.json,1791481835.025904,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu,none,34.86248302734587,0.01605266122524457,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/80dfea12bb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-10.883962.json,1791483372.444452,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6160269417515172,0.0038493361146264547,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/80dfea12bb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-10.883962.json,1791483372.444452,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17537681118609755,0.004610481744649922,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/80dfea12bb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-10.883962.json,1791483372.444452,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.15186841830775,0.0111150292124971,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/80dfea12bb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-10.883962.json,1791483372.444452,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu,none,22.59216461381713,0.015839398903406278,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ba1f464e59/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-33.898704.json,1791483515.092917,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.497277546809728,0.004506690383810748,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ba1f464e59/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-33.898704.json,1791483515.092917,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.09621477006728367,0.003937759506665451,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ba1f464e59/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-33.898704.json,1791483515.092917,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,49.18294968023838,0.011976408761022213,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ba1f464e59/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-33.898704.json,1791483515.092917,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu,none,50.55413030760808,0.021142012497013085,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/20033ecca0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-25.519957.json,1791481946.869679,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.728446614960066,0.004492213966524251,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/20033ecca0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-25.519957.json,1791481946.869679,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.34367566402865546,0.007558841966249079,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/20033ecca0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-25.519957.json,1791481946.869679,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.1997877887386,0.013664754568524406,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/20033ecca0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-25.519957.json,1791481946.869679,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu,none,41.312389529137576,0.018998482251949198,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6d35265020/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-12.278475.json,1791482053.509033,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6534737262115041,0.004455717160782966,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6d35265020/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-12.278475.json,1791482053.509033,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2563637078595928,0.006303588871594172,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6d35265020/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-12.278475.json,1791482053.509033,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.37020076298751,0.013235765300898096,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6d35265020/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-12.278475.json,1791482053.509033,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu,none,34.34712865851215,0.021078895337234414,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6ca50a994c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-56.677383.json,1791482037.51689,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5979258508196639,0.005281395394883163,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6ca50a994c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-56.677383.json,1791482037.51689,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.19552334234556734,0.0063815573201436325,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6ca50a994c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-56.677383.json,1791482037.51689,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.21455720636435,0.014797318468542132,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/6ca50a994c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-56.677383.json,1791482037.51689,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.133079262498544,0.01816998165444306,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/712fd3164a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-48.396444.json,1791482149.225246,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5844064886931907,0.004918399402379144,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/712fd3164a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-48.396444.json,1791482149.225246,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1651931404483456,0.005518915837743687,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/712fd3164a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-48.396444.json,1791482149.225246,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.111547022497,0.013457917064981291,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/712fd3164a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-48.396444.json,1791482149.225246,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu,none,28.85223618510714,0.013135044277901657,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/42361509e7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-09.203286.json,1791483850.062351,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5748686342670232,0.003568842710741213,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/42361509e7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-09.203286.json,1791483850.062351,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.13646366883771094,0.0037237847338416957,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/42361509e7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-09.203286.json,1791483850.062351,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.452086937581015,0.00992008942636653,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/42361509e7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-24-09.203286.json,1791483850.062351,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu,none,35.64064565750435,0.01854191669846348,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/22549527cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-03.492966.json,1791483604.344727,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.616393275500926,0.00461389907865215,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/22549527cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-03.492966.json,1791483604.344727,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.19641977661899518,0.005537583204334378,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/22549527cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-03.492966.json,1791483604.344727,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,59.62955633862047,0.012954036515586777,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/22549527cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-03.492966.json,1791483604.344727,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu,none,46.281825817887004,0.019816048536145322,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/8992841b4c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-39.726010.json,1791483521.303167,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.691670787336196,0.0043913681578613036,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/8992841b4c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-39.726010.json,1791483521.303167,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2907571818848588,0.006780670436583374,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/8992841b4c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-39.726010.json,1791483521.303167,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.83594651869905,0.013128467361701698,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/8992841b4c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-39.726010.json,1791483521.303167,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu,none,25.196494375455174,0.018757906902697068,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/f0fe671560/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-14.491513.json,1791483375.641728,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5380687243143533,0.005076904842326993,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/f0fe671560/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-14.491513.json,1791483375.641728,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11706961969601293,0.005064572107657947,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/f0fe671560/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-14.491513.json,1791483375.641728,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.797298993714925,0.013268766143222914,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/f0fe671560/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-14.491513.json,1791483375.641728,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu,none,29.80077698782273,0.018738878316352132,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/3be2d46786/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-38.700217.json,1791482139.962031,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.5540007386387271,0.004934287432212887,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/3be2d46786/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-38.700217.json,1791482139.962031,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.14609021310797862,0.004955878789801476,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/3be2d46786/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-38.700217.json,1791482139.962031,1 +v1annealCT_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,54.99410586789549,0.013390820186490373,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/3be2d46786/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-38.700217.json,1791482139.962031,1 +v1annealCT_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.378578273248664,0.01846658201636084,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/bf6214f932/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-18.424764.json,1791483499.401418,1 +v1annealCT_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6755831678965258,0.004264707136616363,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/bf6214f932/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-18.424764.json,1791483499.401418,1 +v1annealCT_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23421928418918334,0.00622364304963128,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/bf6214f932/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-18.424764.json,1791483499.401418,1 +v1annealCT_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.890161462063155,0.01280517322863608,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/bf6214f932/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-18.424764.json,1791483499.401418,1 +v1annealCT_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.499505601143234,0.018096889064274084,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/29f76c20a1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-40.834648.json,1791481961.682946,1 +v1annealCT_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6270214305856303,0.0044466866765866305,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/29f76c20a1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-40.834648.json,1791481961.682946,1 +v1annealCT_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18778644289660862,0.005566251300361304,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/29f76c20a1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-40.834648.json,1791481961.682946,1 +v1annealCT_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.94343447430064,0.013571805002280255,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/29f76c20a1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-40.834648.json,1791481961.682946,1 +v1annealCT_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.13942185244085,0.017793060090523307,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/00c60e64ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-43.538950.json,1791483644.663875,1 +v1annealCT_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6534073131571309,0.004323283267821436,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/00c60e64ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-43.538950.json,1791483644.663875,1 +v1annealCT_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20999173362061893,0.005989280158200491,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/00c60e64ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-43.538950.json,1791483644.663875,1 +v1annealCT_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.38288232895476,0.012716432943936958,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/00c60e64ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-20-43.538950.json,1791483644.663875,1 +v1annealCT_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,47.9281177626886,0.020525678471531517,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ff70ca643a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-21.264599.json,1791483562.114695,1 +v1annealCT_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7270509215515971,0.00430811793529823,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ff70ca643a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-21.264599.json,1791483562.114695,1 +v1annealCT_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3165023932990367,0.007021944614804593,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ff70ca643a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-21.264599.json,1791483562.114695,1 +v1annealCT_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.25948317279,0.013846279267236482,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/ff70ca643a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-21.264599.json,1791483562.114695,1 +v1annealCT_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.325230152426116,0.021723882855371978,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/2115b6e429/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-36.991731.json,1791481958.008949,1 +v1annealCT_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7058774329318227,0.004509311390821583,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/2115b6e429/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-36.991731.json,1791481958.008949,1 +v1annealCT_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2924130827510343,0.007251010394083505,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/2115b6e429/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-36.991731.json,1791481958.008949,1 +v1annealCT_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.3956690357591,0.014392674368629996,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/2115b6e429/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-36.991731.json,1791481958.008949,1 +v1annealCT_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.36478361693884,0.017949456464103695,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a9c549156b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-25.644694.json,1791482126.633949,1 +v1annealCT_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7049600321997708,0.003945450888823794,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a9c549156b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-25.644694.json,1791482126.633949,1 +v1annealCT_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.27444138880259233,0.0064101387048091955,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a9c549156b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-25.644694.json,1791482126.633949,1 +v1annealCT_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.6162516123597,0.011665477782777928,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a9c549156b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-55-25.644694.json,1791482126.633949,1 +v1annealCT_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,41.06346749649541,0.018873414664388577,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/bdd68bac57/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-36.500017.json,1791481957.572764,1 +v1annealCT_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6762149684116663,0.004223613103515843,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/bdd68bac57/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-36.500017.json,1791481957.572764,1 +v1annealCT_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23736620836886316,0.006213452753008825,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/bdd68bac57/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-36.500017.json,1791481957.572764,1 +v1annealCT_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.17723072746085,0.013062366573667153,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/bdd68bac57/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-36.500017.json,1791481957.572764,1 +v1annealCT_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.58073850158999,0.018350976221035112,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/60f3722fee/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-54.451516.json,1791481975.694802,1 +v1annealCT_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6591652442353988,0.004395910991262699,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/60f3722fee/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-54.451516.json,1791481975.694802,1 +v1annealCT_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21884843834115342,0.005959730865204717,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/60f3722fee/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-54.451516.json,1791481975.694802,1 +v1annealCT_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.451410066872015,0.012980287745251454,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/60f3722fee/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-54.451516.json,1791481975.694802,1 +v1annealCT_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.363687440812626,0.020091009355568536,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a64959373b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-56.087386.json,1791483836.961126,1 +v1annealCT_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6561553020168169,0.0044363865127961845,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a64959373b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-56.087386.json,1791483836.961126,1 +v1annealCT_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22625245643161188,0.006304840781176882,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a64959373b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-56.087386.json,1791483836.961126,1 +v1annealCT_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.67354504351892,0.014010164707057753,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a64959373b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-56.087386.json,1791483836.961126,1 +v1annealCT_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.60102613621447,0.017098182369410582,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7f6af4ead2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-30.647859.json,1791481951.513893,1 +v1annealCT_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6519916593448345,0.00393679860788899,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7f6af4ead2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-30.647859.json,1791481951.513893,1 +v1annealCT_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2011230671496659,0.005285547439900983,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7f6af4ead2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-30.647859.json,1791481951.513893,1 +v1annealCT_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.192578998640926,0.012268994008151249,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7f6af4ead2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-30.647859.json,1791481951.513893,1 +v1annealCT_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,21.19299919619554,0.01770715340737234,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/62d9a55d34/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-31-16.711076.json,1791484277.361405,1 +v1annealCT_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5105310643429453,0.004648310220770497,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/62d9a55d34/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-31-16.711076.json,1791484277.361405,1 +v1annealCT_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.0866813460153533,0.0038590196661909453,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/62d9a55d34/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-31-16.711076.json,1791484277.361405,1 +v1annealCT_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,47.37869493223841,0.013764622927854048,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/62d9a55d34/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-31-16.711076.json,1791484277.361405,1 +v1annealCT_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.70488031899095,0.01939146999971326,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/18c19b0a6e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-13.079960.json,1791483493.977743,1 +v1annealCT_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.643645687145697,0.004482301430863748,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/18c19b0a6e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-13.079960.json,1791483493.977743,1 +v1annealCT_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21080249776580512,0.005950218237564086,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/18c19b0a6e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-13.079960.json,1791483493.977743,1 +v1annealCT_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.852190330094466,0.01403298181273343,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/18c19b0a6e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-13.079960.json,1791483493.977743,1 +v1annealCT_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.260960635295916,0.019589362084286244,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/84e15895d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-22-09.507428.json,1791483731.26255,1 +v1annealCT_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6701940326913804,0.004407256649854628,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/84e15895d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-22-09.507428.json,1791483731.26255,1 +v1annealCT_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2353608477056684,0.006286126166439239,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/84e15895d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-22-09.507428.json,1791483731.26255,1 +v1annealCT_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.51109470574205,0.013894423560722784,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/84e15895d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-22-09.507428.json,1791483731.26255,1 +v1annealCT_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.45504843715013,0.018815564903394567,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/36792a1d89/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-29.283343.json,1791483390.144703,1 +v1annealCT_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7165743379100451,0.00379665792090343,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/36792a1d89/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-29.283343.json,1791483390.144703,1 +v1annealCT_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2898573300701158,0.006324631714031764,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/36792a1d89/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-29.283343.json,1791483390.144703,1 +v1annealCT_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.43093962822829,0.012424667917856094,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/36792a1d89/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-16-29.283343.json,1791483390.144703,1 +v1annealCT_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,58.569976275354776,0.020125891116371652,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5835ed16c8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-22.742998.json,1791483563.595496,1 +v1annealCT_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7886855421565433,0.0037802768896753078,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5835ed16c8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-22.742998.json,1791483563.595496,1 +v1annealCT_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.4284832409032671,0.007562636112368261,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5835ed16c8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-22.742998.json,1791483563.595496,1 +v1annealCT_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,77.00018175056293,0.012172469342681187,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5835ed16c8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-22.742998.json,1791483563.595496,1 +v1annealCT_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.07570941804086,0.018500995104675903,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7744a94bb6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-57.643883.json,1791483598.442736,1 +v1annealCT_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6218066987870126,0.004383568508498965,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7744a94bb6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-57.643883.json,1791483598.442736,1 +v1annealCT_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17878287176557822,0.005392484635019512,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7744a94bb6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-57.643883.json,1791483598.442736,1 +v1annealCT_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.08680249292363,0.013451000924410251,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7744a94bb6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-19-57.643883.json,1791483598.442736,1 +v1annealCT_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.89757765924292,0.018397674587876715,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/1ced8660be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-39.649698.json,1791482080.508313,1 +v1annealCT_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7079886850243142,0.003895800101196359,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/1ced8660be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-39.649698.json,1791482080.508313,1 +v1annealCT_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2909339610011149,0.006261982855520287,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/1ced8660be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-39.649698.json,1791482080.508313,1 +v1annealCT_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.04537362179224,0.012264690321514308,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/1ced8660be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-54-39.649698.json,1791482080.508313,1 +v1annealCT_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.183369599145685,0.017719548583135458,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/305b0ed26b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-25.522855.json,1791483806.374126,1 +v1annealCT_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6176608431794532,0.004356146453721268,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/305b0ed26b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-25.522855.json,1791483806.374126,1 +v1annealCT_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17368937877200208,0.005313751019317071,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/305b0ed26b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-25.522855.json,1791483806.374126,1 +v1annealCT_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.08428588057238,0.0126566041454882,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/305b0ed26b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-25.522855.json,1791483806.374126,1 +v1annealCT_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,52.009610586054954,0.019477425535442534,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/b443024ed2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-28.761419.json,1791483809.620805,1 +v1annealCT_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7531245633548723,0.003977208748899616,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/b443024ed2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-28.761419.json,1791483809.620805,1 +v1annealCT_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.351835863007656,0.0069924081864659,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/b443024ed2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-28.761419.json,1791483809.620805,1 +v1annealCT_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.36121752728184,0.0129639001501083,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/b443024ed2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-28.761419.json,1791483809.620805,1 +v1annealCT_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.93636345510655,0.0190851844506023,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7a686ad650/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-35.894708.json,1791481957.122603,1 +v1annealCT_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7226075235261146,0.0040194237598737605,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7a686ad650/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-35.894708.json,1791481957.122603,1 +v1annealCT_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2981021765302038,0.006663206461241115,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7a686ad650/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-35.894708.json,1791481957.122603,1 +v1annealCT_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.17394077780446,0.012546076352347852,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7a686ad650/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-35.894708.json,1791481957.122603,1 +v1annealCT_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,42.264403080873244,0.0192815698792672,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e30b1be716/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-26.934175.json,1791481947.737822,1 +v1annealCT_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6867447424557568,0.004263141301660121,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e30b1be716/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-26.934175.json,1791481947.737822,1 +v1annealCT_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2498417150799327,0.006393204004718515,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e30b1be716/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-26.934175.json,1791481947.737822,1 +v1annealCT_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.39330798014066,0.013024291618853545,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/e30b1be716/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-26.934175.json,1791481947.737822,1 +v1annealCT_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.38951270048335,0.018523447079570567,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/261933264e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-15-36.664637.json,1791483337.750387,1 +v1annealCT_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6626000816905984,0.004113482253886594,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/261933264e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-15-36.664637.json,1791483337.750387,1 +v1annealCT_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21556230130127074,0.005750841493558161,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/261933264e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-15-36.664637.json,1791483337.750387,1 +v1annealCT_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.498370183733506,0.012774082864298136,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/261933264e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-15-36.664637.json,1791483337.750387,1 +v1annealCT_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.620469831189965,0.01691590970226963,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c4c8c9dcf8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-17.453770.json,1791483498.322664,1 +v1annealCT_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6321639157529332,0.003925131864566917,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c4c8c9dcf8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-17.453770.json,1791483498.322664,1 +v1annealCT_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17628179172532815,0.005015289442621109,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c4c8c9dcf8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-17.453770.json,1791483498.322664,1 +v1annealCT_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.21728618033199,0.011575065481734917,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/c4c8c9dcf8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-18-17.453770.json,1791483498.322664,1 +v1annealCT_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,47.1529280471397,0.01858922640627089,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a7c965d6af/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-11.034067.json,1791481992.121904,1 +v1annealCT_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7237817887842883,0.004023251421254733,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a7c965d6af/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-11.034067.json,1791481992.121904,1 +v1annealCT_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3010750580998903,0.006807002964948281,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a7c965d6af/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-11.034067.json,1791481992.121904,1 +v1annealCT_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.0078372650961,0.01212456276008217,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/a7c965d6af/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-53-11.034067.json,1791481992.121904,1 +v1annealCT_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,50.83137892255917,0.019666747185566304,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5cfc83632f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-23.663998.json,1791481944.513459,1 +v1annealCT_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7412921167449587,0.003918825069372761,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5cfc83632f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-23.663998.json,1791481944.513459,1 +v1annealCT_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3347841025956057,0.006993754773238128,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5cfc83632f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-23.663998.json,1791481944.513459,1 +v1annealCT_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.93194253017437,0.012738902223069245,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/5cfc83632f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-52-23.663998.json,1791481944.513459,1 +v1annealCT_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.15565004712284,0.01878818251304637,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/2700565b73/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-12.314107.json,1791483793.169462,1 +v1annealCT_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6756829907725556,0.004327298118744849,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/2700565b73/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-12.314107.json,1791483793.169462,1 +v1annealCT_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23566819447437934,0.0062813890368933764,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/2700565b73/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-12.314107.json,1791483793.169462,1 +v1annealCT_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.43522327657075,0.013393881183598322,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/2700565b73/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-23-12.314107.json,1791483793.169462,1 +v1annealCT_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.27714326414332,0.018694414960949198,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7228c401a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-25.943230.json,1791483687.112469,1 +v1annealCT_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6954170161018253,0.0041338072939080765,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7228c401a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-25.943230.json,1791483687.112469,1 +v1annealCT_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2635217621297136,0.0063473638217733525,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7228c401a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-25.943230.json,1791483687.112469,1 +v1annealCT_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.06641689352881,0.012714770409463333,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/7228c401a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-21-25.943230.json,1791483687.112469,1 +v1annealCT_merge3_116k_120k,global_mgsm_ca,5,lm-eval,vllm,,exact_match,flexible-extract,0.352,0.03026628805735995,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ab9c681f46_2026-10-08T17-39-25.080286.json,1791480984.2619321,1 +v1annealCT_merge3_116k_120k,global_mgsm_cs,5,lm-eval,vllm,,exact_match,flexible-extract,0.328,0.02975239182447539,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/520f385506_2026-10-08T18-11-53.869008.json,1791482933.3917418,1 +v1annealCT_merge3_116k_120k,global_mgsm_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.364,0.030491555220405572,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8648e6b195_2026-10-08T17-39-16.861859.json,1791480973.9094565,1 +v1annealCT_merge3_116k_120k,global_mgsm_el,5,lm-eval,vllm,,exact_match,flexible-extract,0.36,0.030418764025175,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4798617d4e_2026-10-08T17-39-17.420847.json,1791480974.8359926,1 +v1annealCT_merge3_116k_120k,global_mgsm_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.332,0.029844039047465916,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/840969ccdc_2026-10-08T17-41-14.539959.json,1791481115.1074252,1 +v1annealCT_merge3_116k_120k,global_mgsm_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.36,0.030418764025175002,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b3f28100ce_2026-10-08T18-00-21.564149.json,1791482236.9079695,1 +v1annealCT_merge3_116k_120k,global_mgsm_eu,5,lm-eval,vllm,,exact_match,flexible-extract,0.336,0.029933259094191516,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4d3698ae6d_2026-10-08T18-09-30.463541.json,1791482797.948203,1 +v1annealCT_merge3_116k_120k,global_mgsm_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.356,0.03034368065715322,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c54e8910c2_2026-10-08T17-41-28.259153.json,1791481114.2324922,1 +v1annealCT_merge3_116k_120k,global_mgsm_gl,5,lm-eval,vllm,,exact_match,flexible-extract,0.344,0.030104503392316392,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/93fab5e8ba_2026-10-08T17-50-48.865810.json,1791481667.1264644,1 +v1annealCT_merge3_116k_120k,global_mgsm_hu,5,lm-eval,vllm,,exact_match,flexible-extract,0.324,0.029658294924545577,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d2000fad66_2026-10-08T18-09-41.267515.json,1791482797.3934166,1 +v1annealCT_merge3_116k_120k,global_mgsm_sr,5,lm-eval,vllm,,exact_match,flexible-extract,0.34,0.030020073605457907,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4ac0f8f7e0_2026-10-08T17-39-24.931350.json,1791480982.8656454,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs,5,lm-eval,vllm,yes,acc,none,0.678963110667996,0.0037505058908490745,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_abstract_algebra,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_business_ethics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_college_biology,5,lm-eval,vllm,,acc,none,0.7916666666666666,0.03396116205845331,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_college_medicine,5,lm-eval,vllm,,acc,none,0.6994219653179191,0.03496101481191176,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_college_physics,5,lm-eval,vllm,,acc,none,0.5490196078431373,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_computer_security,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7574468085106383,0.02802022627120023,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_econometrics,5,lm-eval,vllm,,acc,none,0.5526315789473685,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6896551724137931,0.03855289616378948,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6455026455026455,0.024636830602842035,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_formal_logic,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.043603148600774626,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_global_facts,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_geography,5,lm-eval,vllm,,acc,none,0.8383838383838383,0.02622591986362927,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7307692307692307,0.022489389793654804,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5074074074074074,0.03048219239519157,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8277310924369747,0.024528664971305403,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_physics,5,lm-eval,vllm,,acc,none,0.5695364238410596,0.04042809961395634,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8550458715596331,0.015094215699700396,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6481481481481481,0.032568505702936484,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8284313725490197,0.026460569561240675,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_human_aging,5,lm-eval,vllm,,acc,none,0.7623318385650224,0.02856807946471428,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_human_sexuality,5,lm-eval,vllm,,acc,none,0.7862595419847328,0.03595461611774691,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_humanities,5,lm-eval,vllm,yes,acc,none,0.6085015940488842,0.006695477131122132,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_jurisprudence,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.0437331304091476,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7177914110429447,0.03536117886664741,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_machine_learning,5,lm-eval,vllm,,acc,none,0.48214285714285715,0.047427623612430116,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_miscellaneous,5,lm-eval,vllm,,acc,none,0.7918263090676884,0.014518592248904028,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_moral_disputes,5,lm-eval,vllm,,acc,none,0.7283236994219653,0.02394851290546838,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_moral_scenarios,5,lm-eval,vllm,,acc,none,0.39664804469273746,0.016361354769822343,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_nutrition,5,lm-eval,vllm,,acc,none,0.7418300653594772,0.025058503316958167,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_other,5,lm-eval,vllm,yes,acc,none,0.704216285806244,0.00791410981962096,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_philosophy,5,lm-eval,vllm,,acc,none,0.752411575562701,0.024513879973621984,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_prehistory,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.02240967454730414,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_professional_accounting,5,lm-eval,vllm,,acc,none,0.450354609929078,0.029680105565029025,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_professional_law,5,lm-eval,vllm,,acc,none,0.48891786179921776,0.012767098998525846,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_professional_medicine,5,lm-eval,vllm,,acc,none,0.6875,0.02815637344037142,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_professional_psychology,5,lm-eval,vllm,,acc,none,0.7156862745098039,0.01824902441120767,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_public_relations,5,lm-eval,vllm,,acc,none,0.6272727272727273,0.04631381319425461,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7819304517387066,0.007313530710011489,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_sociology,5,lm-eval,vllm,,acc,none,0.8557213930348259,0.024845753212306015,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_stem,5,lm-eval,vllm,yes,acc,none,0.6587377101173486,0.008210377644202497,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_cs_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3c00d7e23d_2026-10-08T17-37-11.808188.json,1791480700.2986357,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de,5,lm-eval,vllm,yes,acc,none,0.6855860988463182,0.0037398535638956828,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_abstract_algebra,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_astronomy,5,lm-eval,vllm,,acc,none,0.7828947368421053,0.03355045304882924,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7358490566037735,0.02713429162874164,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_college_biology,5,lm-eval,vllm,,acc,none,0.7916666666666666,0.03396116205845331,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_college_mathematics,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_college_physics,5,lm-eval,vllm,,acc,none,0.5490196078431373,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7702127659574468,0.0275017529444124,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_econometrics,5,lm-eval,vllm,,acc,none,0.6052631578947368,0.04598188057816546,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_electrical_engineering,5,lm-eval,vllm,,acc,none,0.696551724137931,0.03831226048850335,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6322751322751323,0.02483383982556237,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_global_facts,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_biology,5,lm-eval,vllm,,acc,none,0.8354838709677419,0.021090847745939306,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6945812807881774,0.032406615658684045,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8363636363636363,0.028887872395487978,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_geography,5,lm-eval,vllm,,acc,none,0.8686868686868687,0.02406315641682249,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9430051813471503,0.01673108529360757,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7487179487179487,0.021992016662370557,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4777777777777778,0.030455413985678415,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.024762902678057915,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_physics,5,lm-eval,vllm,,acc,none,0.6225165562913907,0.03958027231121572,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8642201834862385,0.014686907556339952,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6203703703703703,0.03309682581119039,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_us_history,5,lm-eval,vllm,,acc,none,0.803921568627451,0.027865942286639318,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_human_aging,5,lm-eval,vllm,,acc,none,0.6771300448430493,0.031381476375754995,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_human_sexuality,5,lm-eval,vllm,,acc,none,0.7480916030534351,0.03807387116306089,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_humanities,5,lm-eval,vllm,yes,acc,none,0.6180658873538789,0.0067212272308903535,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_international_law,5,lm-eval,vllm,,acc,none,0.7933884297520661,0.03695980128098826,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_jurisprudence,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.0437331304091476,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_machine_learning,5,lm-eval,vllm,,acc,none,0.5178571428571429,0.047427623612430116,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_marketing,5,lm-eval,vllm,,acc,none,0.8803418803418803,0.021262719400406926,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_miscellaneous,5,lm-eval,vllm,,acc,none,0.8033205619412516,0.014214138556913851,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_moral_disputes,5,lm-eval,vllm,,acc,none,0.7601156069364162,0.02298959254312351,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4480446927374302,0.01663197662893058,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_nutrition,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.025360603796242578,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_other,5,lm-eval,vllm,yes,acc,none,0.7032507241712262,0.007926999790049854,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_prehistory,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.023132376234543416,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_professional_accounting,5,lm-eval,vllm,,acc,none,0.4787234042553192,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_professional_law,5,lm-eval,vllm,,acc,none,0.4876140808344198,0.012766317315473681,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_professional_medicine,5,lm-eval,vllm,,acc,none,0.6544117647058824,0.0288881931039887,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_professional_psychology,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.01784808957491327,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_security_studies,5,lm-eval,vllm,,acc,none,0.7428571428571429,0.027979823538744557,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7949301267468313,0.007147831819420436,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_sociology,5,lm-eval,vllm,,acc,none,0.8805970149253731,0.022928793277219726,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_stem,5,lm-eval,vllm,yes,acc,none,0.6622264509990485,0.008193969618745345,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_de_world_religions,5,lm-eval,vllm,,acc,none,0.8421052631578947,0.027966785859160903,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e4aa7b2d2_2026-10-08T18-03-22.247461.json,1791482232.3814018,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el,5,lm-eval,vllm,yes,acc,none,0.6701324597635664,0.0038158837112437813,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_abstract_algebra,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_anatomy,5,lm-eval,vllm,,acc,none,0.5851851851851851,0.04256193767901412,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_astronomy,5,lm-eval,vllm,,acc,none,0.8289473684210527,0.03064360707167711,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.690566037735849,0.028450154794118682,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_college_chemistry,5,lm-eval,vllm,,acc,none,0.55,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_college_computer_science,5,lm-eval,vllm,,acc,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_college_mathematics,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_college_medicine,5,lm-eval,vllm,,acc,none,0.6473988439306358,0.03643037168958545,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_college_physics,5,lm-eval,vllm,,acc,none,0.5686274509803921,0.049280995972875316,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_computer_security,5,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7319148936170212,0.028957342788342354,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_econometrics,5,lm-eval,vllm,,acc,none,0.5175438596491229,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6620689655172414,0.03941707632064884,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.02487081525105711,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_formal_logic,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.044444444444444446,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_global_facts,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6502463054187192,0.033554009049695604,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_geography,5,lm-eval,vllm,,acc,none,0.8434343434343434,0.025890520358141458,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8911917098445595,0.02247325333276875,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7666666666666667,0.021444547301560507,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5037037037037037,0.030484701665084428,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8109243697478992,0.025435119438105305,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_physics,5,lm-eval,vllm,,acc,none,0.5894039735099338,0.04016689594849927,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8220183486238533,0.016399436366612896,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8438818565400844,0.02362715946031866,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_human_aging,5,lm-eval,vllm,,acc,none,0.7130044843049327,0.030360379710291947,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_human_sexuality,5,lm-eval,vllm,,acc,none,0.7404580152671756,0.03844876139785267,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_humanities,5,lm-eval,vllm,yes,acc,none,0.6114771519659936,0.006782698511880605,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_jurisprudence,5,lm-eval,vllm,,acc,none,0.7592592592592593,0.041331194402438355,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_medical_genetics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_miscellaneous,5,lm-eval,vllm,,acc,none,0.722860791826309,0.01600563629412252,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_moral_disputes,5,lm-eval,vllm,,acc,none,0.7312138728323699,0.02386800326250009,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_moral_scenarios,5,lm-eval,vllm,,acc,none,0.45139664804469276,0.01664330737231585,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_nutrition,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.025646863097137932,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_other,5,lm-eval,vllm,yes,acc,none,0.6723527518506598,0.008222531920659526,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_prehistory,5,lm-eval,vllm,,acc,none,0.7098765432098766,0.025251173936494977,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_professional_accounting,5,lm-eval,vllm,,acc,none,0.45390070921985815,0.029700453247291494,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_professional_law,5,lm-eval,vllm,,acc,none,0.4921773142112125,0.012768673076111898,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_professional_medicine,5,lm-eval,vllm,,acc,none,0.6397058823529411,0.02916312857067069,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_professional_psychology,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.019070985589687436,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_public_relations,5,lm-eval,vllm,,acc,none,0.7454545454545455,0.04172343038705381,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_security_studies,5,lm-eval,vllm,,acc,none,0.8,0.02560737598657919,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7705557361065973,0.007445918591652987,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_stem,5,lm-eval,vllm,yes,acc,none,0.6574690770694577,0.00824064090009487,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_el_world_religions,5,lm-eval,vllm,,acc,none,0.8011695906432749,0.030611116557432514,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7055492393_2026-10-08T17-54-30.216016.json,1791481671.6276715,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en,5,lm-eval,vllm,yes,acc,none,0.7309500071214927,0.0035795497501065914,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_abstract_algebra,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_anatomy,5,lm-eval,vllm,,acc,none,0.6370370370370371,0.041539484047424,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_astronomy,5,lm-eval,vllm,,acc,none,0.8157894736842105,0.031546980450822305,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_business_ethics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7547169811320755,0.026480357179895737,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_college_biology,5,lm-eval,vllm,,acc,none,0.8194444444444444,0.03216600808802272,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_college_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_college_medicine,5,lm-eval,vllm,,acc,none,0.7283236994219653,0.03391750322321658,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_college_physics,5,lm-eval,vllm,,acc,none,0.5784313725490197,0.049135952012745024,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_computer_security,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7872340425531915,0.02675439134803978,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_econometrics,5,lm-eval,vllm,,acc,none,0.6578947368421053,0.044629175353369355,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7793103448275862,0.03455930201924806,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6798941798941799,0.024026846392873506,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_formal_logic,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.04216370213557839,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_global_facts,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_biology,5,lm-eval,vllm,,acc,none,0.8838709677419355,0.01822575794943229,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.7093596059113301,0.031947400722655415,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8424242424242424,0.02845038880528439,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_geography,5,lm-eval,vllm,,acc,none,0.9040404040404041,0.0209848086100479,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9481865284974094,0.01599622932024413,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7897435897435897,0.020660597485026883,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5074074074074074,0.03048219239519157,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.9117647058823529,0.018424189175962204,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_physics,5,lm-eval,vllm,,acc,none,0.5695364238410596,0.04042809961395634,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8752293577981651,0.014168298359156423,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7268518518518519,0.030388051301678112,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8872549019607843,0.022198571039456782,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_high_school_world_history,5,lm-eval,vllm,,acc,none,0.890295358649789,0.02034340073486879,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_human_aging,5,lm-eval,vllm,,acc,none,0.7847533632286996,0.027584066602208322,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_humanities,5,lm-eval,vllm,yes,acc,none,0.6820403825717322,0.0064916972547712105,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_jurisprudence,5,lm-eval,vllm,,acc,none,0.8148148148148148,0.03755265865037181,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_logical_fallacies,5,lm-eval,vllm,,acc,none,0.8098159509202454,0.03083349114628123,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_management,5,lm-eval,vllm,,acc,none,0.7961165048543689,0.0398913985953177,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_marketing,5,lm-eval,vllm,,acc,none,0.8675213675213675,0.022209309073165668,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_medical_genetics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_miscellaneous,5,lm-eval,vllm,,acc,none,0.8505747126436781,0.012748670802527031,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_moral_disputes,5,lm-eval,vllm,,acc,none,0.7861271676300579,0.022075709251757194,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5497206703910614,0.01663961523684584,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_nutrition,5,lm-eval,vllm,,acc,none,0.7745098039215687,0.023929155517351218,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_other,5,lm-eval,vllm,yes,acc,none,0.7457354361120051,0.007520485739635024,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_philosophy,5,lm-eval,vllm,,acc,none,0.7813504823151125,0.02347558141786108,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_prehistory,5,lm-eval,vllm,,acc,none,0.8302469135802469,0.020888690414093802,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_professional_accounting,5,lm-eval,vllm,,acc,none,0.5177304964539007,0.02980873964223769,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_professional_law,5,lm-eval,vllm,,acc,none,0.5547588005215124,0.01269342130397317,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_professional_medicine,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.026799562024887664,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_professional_psychology,5,lm-eval,vllm,,acc,none,0.7630718954248366,0.017201662169789703,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8261293467663309,0.006707207581898258,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_sociology,5,lm-eval,vllm,,acc,none,0.8805970149253731,0.022928793277219726,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_stem,5,lm-eval,vllm,yes,acc,none,0.6964795432921027,0.007907860420746728,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_en_world_religions,5,lm-eval,vllm,,acc,none,0.8421052631578947,0.027966785859160903,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0e04c083c4_2026-10-08T17-55-50.671906.json,1791481809.670569,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es,5,lm-eval,vllm,yes,acc,none,0.6927788064378294,0.003697281754655084,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_abstract_algebra,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_astronomy,5,lm-eval,vllm,,acc,none,0.8289473684210527,0.03064360707167711,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7245283018867924,0.027495663683724022,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_college_computer_science,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_college_medicine,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.03414014007044037,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7702127659574468,0.0275017529444124,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_econometrics,5,lm-eval,vllm,,acc,none,0.6578947368421053,0.044629175353369355,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.02467786284133279,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_formal_logic,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.04285714285714286,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_biology,5,lm-eval,vllm,,acc,none,0.864516129032258,0.01946933458648694,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6600985221674877,0.03332769068410796,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8424242424242424,0.02845038880528439,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_geography,5,lm-eval,vllm,,acc,none,0.8686868686868687,0.02406315641682249,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7717948717948718,0.02127839386358626,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4888888888888889,0.030478009819615792,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8445378151260504,0.023536818625398935,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_physics,5,lm-eval,vllm,,acc,none,0.609271523178808,0.039837983066598075,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8807339449541285,0.013895729292589025,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7083333333333334,0.030998666304560565,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8480392156862745,0.025195658428931827,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8523206751054853,0.023094329582595715,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_human_aging,5,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_humanities,5,lm-eval,vllm,yes,acc,none,0.6180658873538789,0.0066715279673026625,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7239263803680982,0.035123852837050454,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_machine_learning,5,lm-eval,vllm,,acc,none,0.5089285714285714,0.04745033255489126,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_management,5,lm-eval,vllm,,acc,none,0.7766990291262136,0.041235531898914324,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_miscellaneous,5,lm-eval,vllm,,acc,none,0.8122605363984674,0.013964393769899023,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_moral_disputes,5,lm-eval,vllm,,acc,none,0.7485549132947977,0.023357365785874006,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_moral_scenarios,5,lm-eval,vllm,,acc,none,0.40893854748603353,0.01644283065471543,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_nutrition,5,lm-eval,vllm,,acc,none,0.7418300653594772,0.025058503316958167,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_other,5,lm-eval,vllm,yes,acc,none,0.718056002574831,0.007812174091441038,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_philosophy,5,lm-eval,vllm,,acc,none,0.7556270096463023,0.024406162094668955,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_prehistory,5,lm-eval,vllm,,acc,none,0.7654320987654321,0.0235768817440057,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_professional_accounting,5,lm-eval,vllm,,acc,none,0.48226950354609927,0.02980873964223769,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_professional_law,5,lm-eval,vllm,,acc,none,0.49934810951760106,0.012770225252255563,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_professional_medicine,5,lm-eval,vllm,,acc,none,0.7242647058823529,0.02714627193662515,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_professional_psychology,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.017555818091322294,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8066298342541437,0.007032862683763749,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_stem,5,lm-eval,vllm,yes,acc,none,0.6682524579765303,0.008102482394086782,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_virology,5,lm-eval,vllm,,acc,none,0.5481927710843374,0.0387437155658795,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_es_world_religions,5,lm-eval,vllm,,acc,none,0.847953216374269,0.027539122889061483,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7cd7d8f3de_2026-10-08T17-44-37.304591.json,1791481116.7146654,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr,5,lm-eval,vllm,yes,acc,none,0.6909984332716137,0.0037292436702404813,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_astronomy,5,lm-eval,vllm,,acc,none,0.8355263157894737,0.030167533468632726,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_business_ethics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7358490566037735,0.02713429162874164,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_college_biology,5,lm-eval,vllm,,acc,none,0.8055555555555556,0.03309615177059002,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_college_chemistry,5,lm-eval,vllm,,acc,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_college_medicine,5,lm-eval,vllm,,acc,none,0.7514450867052023,0.03295304696818318,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7659574468085106,0.02767845257821238,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_econometrics,5,lm-eval,vllm,,acc,none,0.5350877192982456,0.04692008381368906,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7172413793103448,0.03752833958003335,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6613756613756614,0.024373197867983004,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_global_facts,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8451612903225807,0.020579287326583217,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6551724137931034,0.03344283744280457,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.030117688929503603,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8535353535353535,0.025190921114603887,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8911917098445595,0.02247325333276875,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7435897435897436,0.022139081103971635,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8067226890756303,0.02564947026588922,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5960264900662252,0.04006485685365344,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8403669724770643,0.015703498348461794,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7268518518518519,0.030388051301678112,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026156867523931024,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8649789029535865,0.022245776632003705,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_human_aging,5,lm-eval,vllm,,acc,none,0.7130044843049327,0.030360379710291947,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7709923664122137,0.036853466317118506,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_humanities,5,lm-eval,vllm,yes,acc,none,0.6329436769394261,0.006660811560673918,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_machine_learning,5,lm-eval,vllm,,acc,none,0.5089285714285714,0.04745033255489126,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_management,5,lm-eval,vllm,,acc,none,0.7961165048543689,0.0398913985953177,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_marketing,5,lm-eval,vllm,,acc,none,0.8632478632478633,0.022509033937077844,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_medical_genetics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_miscellaneous,5,lm-eval,vllm,,acc,none,0.8007662835249042,0.014283378044296373,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7774566473988439,0.022394215661942808,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.47262569832402235,0.016697420650642742,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_nutrition,5,lm-eval,vllm,,acc,none,0.7516339869281046,0.02473998135511354,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_other,5,lm-eval,vllm,yes,acc,none,0.7125844866430641,0.007842098902002327,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_philosophy,5,lm-eval,vllm,,acc,none,0.729903536977492,0.02521804037341055,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_prehistory,5,lm-eval,vllm,,acc,none,0.7993827160493827,0.022282313949774837,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_professional_accounting,5,lm-eval,vllm,,acc,none,0.4787234042553192,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_professional_law,5,lm-eval,vllm,,acc,none,0.4980443285528031,0.012770138422208597,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_professional_medicine,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.027678468642144703,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_professional_psychology,5,lm-eval,vllm,,acc,none,0.696078431372549,0.018607552131279893,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_public_relations,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.04350271442923247,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_security_studies,5,lm-eval,vllm,,acc,none,0.8122448979591836,0.025000256039546167,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.777705557361066,0.007377058971967036,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_stem,5,lm-eval,vllm,yes,acc,none,0.6717411988582302,0.008093033593612346,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_fr_world_religions,5,lm-eval,vllm,,acc,none,0.847953216374269,0.027539122889061483,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b709cc1cd7_2026-10-08T18-15-16.724197.json,1791482936.1227205,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it,5,lm-eval,vllm,yes,acc,none,0.6863694630394531,0.0037140299910219114,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_abstract_algebra,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_college_physics,5,lm-eval,vllm,,acc,none,0.5294117647058824,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_computer_security,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7957446808510639,0.02635515841334947,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_econometrics,5,lm-eval,vllm,,acc,none,0.5789473684210527,0.04644602091222323,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7172413793103448,0.03752833958003335,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.024552292209342713,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_global_facts,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_biology,5,lm-eval,vllm,,acc,none,0.8870967741935484,0.01800360332586356,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6699507389162561,0.033085304262282594,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_geography,5,lm-eval,vllm,,acc,none,0.8787878787878788,0.02325315795194205,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9067357512953368,0.020986854593289705,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7564102564102564,0.021763733684173926,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8319327731092437,0.024289102115692317,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8440366972477065,0.015555802713590066,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6898148148148148,0.03154696285656624,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8676470588235294,0.02378429752091887,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_human_aging,5,lm-eval,vllm,,acc,none,0.6995515695067265,0.030769352008229164,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_human_sexuality,5,lm-eval,vllm,,acc,none,0.732824427480916,0.03880848301082397,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_humanities,5,lm-eval,vllm,yes,acc,none,0.6131774707757705,0.006640214659458969,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_machine_learning,5,lm-eval,vllm,,acc,none,0.5178571428571429,0.047427623612430116,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_management,5,lm-eval,vllm,,acc,none,0.7766990291262136,0.041235531898914324,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_medical_genetics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_miscellaneous,5,lm-eval,vllm,,acc,none,0.8109833971902938,0.014000791294407068,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3854748603351955,0.01627792703963812,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_nutrition,5,lm-eval,vllm,,acc,none,0.7516339869281046,0.02473998135511354,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_other,5,lm-eval,vllm,yes,acc,none,0.7051818474412617,0.00795163455110971,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_prehistory,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.02277971908873342,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_professional_accounting,5,lm-eval,vllm,,acc,none,0.5,0.029827499313594685,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_professional_law,5,lm-eval,vllm,,acc,none,0.4934810951760104,0.012769150688867309,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_professional_medicine,5,lm-eval,vllm,,acc,none,0.6911764705882353,0.028064998167040053,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_professional_psychology,5,lm-eval,vllm,,acc,none,0.7418300653594772,0.0177045316532501,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_security_studies,5,lm-eval,vllm,,acc,none,0.8,0.02560737598657919,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7949301267468313,0.00717774698264795,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_sociology,5,lm-eval,vllm,,acc,none,0.8557213930348259,0.024845753212306015,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_stem,5,lm-eval,vllm,yes,acc,none,0.6711068823342848,0.008058815840081083,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_it_world_religions,5,lm-eval,vllm,,acc,none,0.847953216374269,0.027539122889061483,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0c2c974ddc_2026-10-08T18-05-36.715136.json,1791482375.778583,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt,5,lm-eval,vllm,yes,acc,none,0.6581683520865973,0.003801347460938871,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7132075471698113,0.027834912527544126,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_college_biology,5,lm-eval,vllm,,acc,none,0.7569444444444444,0.03586879280080337,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_college_computer_science,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_college_medicine,5,lm-eval,vllm,,acc,none,0.6473988439306358,0.03643037168958545,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_college_physics,5,lm-eval,vllm,,acc,none,0.47058823529411764,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7829787234042553,0.026947483121496238,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_econometrics,5,lm-eval,vllm,,acc,none,0.5263157894736842,0.04697085136647865,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6551724137931034,0.03960933549451213,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6402116402116402,0.024718075944129204,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_formal_logic,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04426266681379905,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8161290322580645,0.022037217340267787,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7256410256410256,0.022622765767493235,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.46296296296296297,0.03040178640610153,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7773109243697479,0.027025433498882392,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_physics,5,lm-eval,vllm,,acc,none,0.5827814569536424,0.040261414976346124,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8403669724770643,0.015703498348461794,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6342592592592593,0.032847388576472014,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7696078431372549,0.029554292605695046,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8312236286919831,0.02438140683258622,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_human_aging,5,lm-eval,vllm,,acc,none,0.6905829596412556,0.031024411740572237,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7709923664122137,0.036853466317118506,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_humanities,5,lm-eval,vllm,yes,acc,none,0.5827842720510096,0.006701273865989164,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6871165644171779,0.03642914578292403,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_machine_learning,5,lm-eval,vllm,,acc,none,0.44642857142857145,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7509578544061303,0.015464676163396064,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.02378620325550823,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.33743016759776534,0.015813901283913096,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_nutrition,5,lm-eval,vllm,,acc,none,0.7124183006535948,0.025917806117147137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_other,5,lm-eval,vllm,yes,acc,none,0.6794335371741229,0.008156642750370343,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_prehistory,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.024659685185967343,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_professional_accounting,5,lm-eval,vllm,,acc,none,0.45390070921985815,0.029700453247291494,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_professional_law,5,lm-eval,vllm,,acc,none,0.4680573663624511,0.012744149704869631,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6727941176470589,0.028501452860396626,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_professional_psychology,5,lm-eval,vllm,,acc,none,0.6928104575163399,0.018663359671463636,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7673058173545662,0.007491326324746716,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_sociology,5,lm-eval,vllm,,acc,none,0.8109452736318408,0.02768691358801299,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_stem,5,lm-eval,vllm,yes,acc,none,0.6431969552806851,0.008280281555403076,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_lt_world_religions,5,lm-eval,vllm,,acc,none,0.847953216374269,0.027539122889061483,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f08e6703ae_2026-10-08T17-34-58.305114.json,1791480549.6999002,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl,5,lm-eval,vllm,yes,acc,none,0.6904287138584247,0.0037421584391734387,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_anatomy,5,lm-eval,vllm,,acc,none,0.6,0.0423207369515159,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_astronomy,5,lm-eval,vllm,,acc,none,0.7763157894736842,0.033911609343436046,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7245283018867924,0.027495663683724022,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_college_biology,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03476590104304133,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_college_computer_science,5,lm-eval,vllm,,acc,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_college_medicine,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.03414014007044037,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_computer_security,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7702127659574468,0.0275017529444124,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7103448275862069,0.03780019230438011,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6534391534391535,0.024508777521028414,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_global_facts,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8483870967741935,0.020402616654416734,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6798029556650246,0.032826493853041455,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8911917098445595,0.02247325333276875,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7666666666666667,0.021444547301560507,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4740740740740741,0.030444528528810785,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.024762902678057915,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_physics,5,lm-eval,vllm,,acc,none,0.5298013245033113,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8587155963302753,0.014933868987028072,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.03114144782353603,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.02675640153807894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8523206751054853,0.023094329582595715,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_human_aging,5,lm-eval,vllm,,acc,none,0.7174887892376681,0.030216831011508755,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_humanities,5,lm-eval,vllm,yes,acc,none,0.632731137088204,0.0067023935613650205,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_jurisprudence,5,lm-eval,vllm,,acc,none,0.8055555555555556,0.038260763248848646,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7300613496932515,0.034878251684978955,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7713920817369093,0.015016884698539887,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7485549132947977,0.023357365785874006,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4681564245810056,0.01668855341561226,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_nutrition,5,lm-eval,vllm,,acc,none,0.7516339869281046,0.02473998135511354,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_other,5,lm-eval,vllm,yes,acc,none,0.7067911168329578,0.007960081057789212,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_philosophy,5,lm-eval,vllm,,acc,none,0.7556270096463023,0.024406162094668955,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_prehistory,5,lm-eval,vllm,,acc,none,0.7746913580246914,0.02324620264781973,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_professional_accounting,5,lm-eval,vllm,,acc,none,0.4929078014184397,0.029824498559128977,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_professional_law,5,lm-eval,vllm,,acc,none,0.5130378096479792,0.01276589388383549,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6985294117647058,0.027875982114273147,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_professional_psychology,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.018054027458815132,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_security_studies,5,lm-eval,vllm,,acc,none,0.8081632653061225,0.0252069631542254,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7929801754956126,0.007197777276241819,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_sociology,5,lm-eval,vllm,,acc,none,0.8557213930348259,0.024845753212306015,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_stem,5,lm-eval,vllm,yes,acc,none,0.6603235014272122,0.008176401409969718,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_virology,5,lm-eval,vllm,,acc,none,0.536144578313253,0.038823108508905954,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_nl_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ac41dbaba_2026-10-08T18-17-24.295594.json,1791483080.5722716,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl,5,lm-eval,vllm,yes,acc,none,0.6776100270616722,0.0037864743869033242,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_anatomy,5,lm-eval,vllm,,acc,none,0.5259259259259259,0.043135316967505756,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_business_ethics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6716981132075471,0.028901593612411777,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_college_biology,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03476590104304133,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7446808510638298,0.0285048564705142,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6551724137931034,0.03960933549451213,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.656084656084656,0.0244644266255964,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_global_facts,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8516129032258064,0.02022273755433042,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6600985221674877,0.03332769068410796,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_geography,5,lm-eval,vllm,,acc,none,0.7878787878787878,0.029126522834586777,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7512820512820513,0.021916957709213813,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5,0.030485538042484616,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7773109243697479,0.027025433498882392,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8733944954128441,0.014257128686165186,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6435185185185185,0.03266478331527272,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8088235294117647,0.02759917430064072,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8565400843881856,0.02281829182101699,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_human_aging,5,lm-eval,vllm,,acc,none,0.7040358744394619,0.03063659134869978,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7404580152671756,0.03844876139785267,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_humanities,5,lm-eval,vllm,yes,acc,none,0.6189160467587673,0.0067799037882603705,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.04414343666854928,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7055214723926381,0.03581165790474083,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_machine_learning,5,lm-eval,vllm,,acc,none,0.5178571428571429,0.047427623612430116,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7701149425287356,0.01504630184669183,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7312138728323699,0.02386800326250009,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5128491620111731,0.01671697883804368,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_nutrition,5,lm-eval,vllm,,acc,none,0.738562091503268,0.025160998214292445,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_other,5,lm-eval,vllm,yes,acc,none,0.6926295461860316,0.00803707756788732,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_philosophy,5,lm-eval,vllm,,acc,none,0.6945337620578779,0.026160584450140488,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_prehistory,5,lm-eval,vllm,,acc,none,0.7438271604938271,0.02428853363772609,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_professional_accounting,5,lm-eval,vllm,,acc,none,0.4574468085106383,0.029719281272236827,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_professional_law,5,lm-eval,vllm,,acc,none,0.4784876140808344,0.012758410941038882,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6801470588235294,0.028332959514031246,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_professional_psychology,5,lm-eval,vllm,,acc,none,0.7091503267973857,0.018373116915903997,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_security_studies,5,lm-eval,vllm,,acc,none,0.7959183673469388,0.02580128347509046,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7793305167370815,0.007363013473074055,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_stem,5,lm-eval,vllm,yes,acc,none,0.6511259118300031,0.008225256341013967,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_virology,5,lm-eval,vllm,,acc,none,0.4759036144578313,0.03887971849597268,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pl_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fc7a9e2c8e_2026-10-08T17-53-48.909941.json,1791481675.1602125,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt,5,lm-eval,vllm,yes,acc,none,0.6932773109243697,0.003706580081183497,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_anatomy,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.04072314811876841,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_astronomy,5,lm-eval,vllm,,acc,none,0.8223684210526315,0.03110318238312337,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7584905660377359,0.02634148037111831,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_computer_security,5,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7702127659574468,0.0275017529444124,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_econometrics,5,lm-eval,vllm,,acc,none,0.5789473684210527,0.04644602091222323,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7034482758620689,0.03806142687309988,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.02487081525105711,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_formal_logic,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.043603148600774626,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_biology,5,lm-eval,vllm,,acc,none,0.867741935483871,0.019272015434846444,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6650246305418719,0.03320852742348313,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8363636363636363,0.028887872395487978,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8737373737373737,0.023664359402880177,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7435897435897436,0.022139081103971635,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4888888888888889,0.030478009819615792,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_physics,5,lm-eval,vllm,,acc,none,0.6357615894039735,0.039291117812427355,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8678899082568807,0.014517801914598314,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8578431372549019,0.024509803921568627,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8438818565400844,0.02362715946031866,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_human_aging,5,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_humanities,5,lm-eval,vllm,yes,acc,none,0.626567481402763,0.006672926469019681,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_jurisprudence,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.03957835471980979,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_management,5,lm-eval,vllm,,acc,none,0.8058252427184466,0.03916667762822582,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_medical_genetics,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_miscellaneous,5,lm-eval,vllm,,acc,none,0.8084291187739464,0.014072859310451928,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7543352601156069,0.023176298203992085,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4491620111731844,0.016635838341631865,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_nutrition,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.024848018263875137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_other,5,lm-eval,vllm,yes,acc,none,0.7151593176697779,0.007821179496889758,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_prehistory,5,lm-eval,vllm,,acc,none,0.7839506172839507,0.02289916291844576,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_professional_accounting,5,lm-eval,vllm,,acc,none,0.48936170212765956,0.029820747191422466,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_professional_law,5,lm-eval,vllm,,acc,none,0.4980443285528031,0.012770138422208597,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6875,0.02815637344037142,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_professional_psychology,5,lm-eval,vllm,,acc,none,0.7418300653594772,0.0177045316532501,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_security_studies,5,lm-eval,vllm,,acc,none,0.7877551020408163,0.026176967197866795,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.79688007799805,0.007144167356173824,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_sociology,5,lm-eval,vllm,,acc,none,0.8557213930348259,0.024845753212306015,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_stem,5,lm-eval,vllm,yes,acc,none,0.6701554075483667,0.008082925300453323,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_virology,5,lm-eval,vllm,,acc,none,0.4819277108433735,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_pt_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a259c5850_2026-10-08T17-37-23.543244.json,1791480695.4901412,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro,5,lm-eval,vllm,yes,acc,none,0.6828087167070218,0.0037395872393806164,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_abstract_algebra,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_anatomy,5,lm-eval,vllm,,acc,none,0.562962962962963,0.042849586397534056,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7245283018867924,0.027495663683724022,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_college_computer_science,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_college_mathematics,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_computer_security,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7446808510638298,0.0285048564705142,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.626984126984127,0.024906990458992587,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_global_facts,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_biology,5,lm-eval,vllm,,acc,none,0.8774193548387097,0.018656720991789427,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6748768472906403,0.03295797566311267,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.927461139896373,0.018718998520678213,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7564102564102564,0.021763733684173926,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5296296296296297,0.030431963547936577,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.024762902678057915,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_physics,5,lm-eval,vllm,,acc,none,0.5629139072847682,0.040500357222306375,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8587155963302753,0.014933868987028072,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8431372549019608,0.02552472232455332,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_human_aging,5,lm-eval,vllm,,acc,none,0.7174887892376681,0.030216831011508755,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_human_sexuality,5,lm-eval,vllm,,acc,none,0.7404580152671756,0.03844876139785267,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_humanities,5,lm-eval,vllm,yes,acc,none,0.6138150903294368,0.006673776613640629,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_jurisprudence,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.040774947092526284,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7361963190184049,0.03462419931615622,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_machine_learning,5,lm-eval,vllm,,acc,none,0.49107142857142855,0.04745033255489126,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_marketing,5,lm-eval,vllm,,acc,none,0.8760683760683761,0.021586494001281407,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_medical_genetics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_miscellaneous,5,lm-eval,vllm,,acc,none,0.7713920817369093,0.015016884698539887,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_moral_disputes,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.02378620325550823,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_moral_scenarios,5,lm-eval,vllm,,acc,none,0.41787709497206704,0.01649540063582002,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_nutrition,5,lm-eval,vllm,,acc,none,0.761437908496732,0.02440439492808785,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_other,5,lm-eval,vllm,yes,acc,none,0.704216285806244,0.007963439067554012,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_philosophy,5,lm-eval,vllm,,acc,none,0.752411575562701,0.024513879973621984,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_prehistory,5,lm-eval,vllm,,acc,none,0.8148148148148148,0.0216138093952248,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_professional_accounting,5,lm-eval,vllm,,acc,none,0.4929078014184397,0.029824498559128977,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_professional_law,5,lm-eval,vllm,,acc,none,0.48239895697522817,0.012762321298823471,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_professional_medicine,5,lm-eval,vllm,,acc,none,0.7022058823529411,0.02777829870154546,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_professional_psychology,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.01843342764940195,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_security_studies,5,lm-eval,vllm,,acc,none,0.7918367346938775,0.02599111767281334,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7871303217419564,0.007246349332451072,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_sociology,5,lm-eval,vllm,,acc,none,0.845771144278607,0.025538433368578303,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_stem,5,lm-eval,vllm,yes,acc,none,0.6628607675229939,0.00816117562008721,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_ro_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9a2f0bfe63_2026-10-08T17-46-52.593150.json,1791481250.9559183,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr,5,lm-eval,vllm,yes,acc,none,0.6670702179176755,0.003828552132021895,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_anatomy,5,lm-eval,vllm,,acc,none,0.5481481481481482,0.04299268905480864,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6641509433962264,0.029067220146644885,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_college_biology,5,lm-eval,vllm,,acc,none,0.7708333333333334,0.03514697467862389,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_college_computer_science,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_college_medicine,5,lm-eval,vllm,,acc,none,0.6589595375722543,0.03614665424180821,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_computer_security,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7361702127659574,0.028809989854102946,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_econometrics,5,lm-eval,vllm,,acc,none,0.5087719298245614,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6068965517241379,0.04070329013707074,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6640211640211641,0.02432631052914909,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_formal_logic,5,lm-eval,vllm,,acc,none,0.5476190476190477,0.04451807959055331,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8290322580645161,0.021417242936321575,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.625615763546798,0.03405155380561957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8535353535353535,0.025190921114603887,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8756476683937824,0.02381447708659357,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7564102564102564,0.021763733684173926,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4666666666666667,0.03041771696171749,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5364238410596026,0.04071636065944211,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8403669724770643,0.015703498348461794,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6620370370370371,0.03225941352631297,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7892156862745098,0.028626547912437423,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8312236286919831,0.02438140683258622,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_human_aging,5,lm-eval,vllm,,acc,none,0.6860986547085202,0.031146796482972486,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7404580152671756,0.03844876139785267,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_humanities,5,lm-eval,vllm,yes,acc,none,0.614240170031881,0.006818190350000062,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7407407407407407,0.04236511258094632,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6687116564417178,0.03697983910025588,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_machine_learning,5,lm-eval,vllm,,acc,none,0.5625,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_management,5,lm-eval,vllm,,acc,none,0.7378640776699029,0.04354631077260595,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_marketing,5,lm-eval,vllm,,acc,none,0.8504273504273504,0.023365051491753757,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_medical_genetics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7164750957854407,0.016117318166832244,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.024105712607754307,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4983240223463687,0.01672240760829654,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_nutrition,5,lm-eval,vllm,,acc,none,0.7287581699346405,0.025457756696667815,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_other,5,lm-eval,vllm,yes,acc,none,0.664306404892179,0.008271540843647458,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_philosophy,5,lm-eval,vllm,,acc,none,0.7331189710610932,0.0251226376088166,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_prehistory,5,lm-eval,vllm,,acc,none,0.7345679012345679,0.024569223600460856,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_professional_accounting,5,lm-eval,vllm,,acc,none,0.46808510638297873,0.02976667507587383,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_professional_law,5,lm-eval,vllm,,acc,none,0.48435462842242505,0.012763982838120936,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6360294117647058,0.029227192460031966,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_professional_psychology,5,lm-eval,vllm,,acc,none,0.696078431372549,0.018607552131279893,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7754306142346441,0.0073893834203624005,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_stem,5,lm-eval,vllm,yes,acc,none,0.6428797970187123,0.008292671508028137,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_virology,5,lm-eval,vllm,,acc,none,0.4759036144578313,0.03887971849597268,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sr_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fefa8a4dd_2026-10-08T18-17-21.802290.json,1791483077.24668,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv,5,lm-eval,vllm,yes,acc,none,0.687152827232588,0.003719758918063427,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_abstract_algebra,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_anatomy,5,lm-eval,vllm,,acc,none,0.5481481481481482,0.04299268905480864,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_business_ethics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7283018867924528,0.027377706624670702,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_college_biology,5,lm-eval,vllm,,acc,none,0.8263888888888888,0.03167473383795719,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_college_computer_science,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_college_mathematics,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_college_medicine,5,lm-eval,vllm,,acc,none,0.6763005780346821,0.03567603799639168,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7617021276595745,0.02785125297388981,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_econometrics,5,lm-eval,vllm,,acc,none,0.5526315789473685,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6896551724137931,0.03855289616378948,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.02391998416404783,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_biology,5,lm-eval,vllm,,acc,none,0.864516129032258,0.01946933458648694,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6995073891625616,0.03225799476233485,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8424242424242424,0.02845038880528439,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_geography,5,lm-eval,vllm,,acc,none,0.8787878787878788,0.02325315795194205,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7333333333333333,0.022421273612923794,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5037037037037037,0.030484701665084428,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8151260504201681,0.025215992877954195,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_physics,5,lm-eval,vllm,,acc,none,0.5894039735099338,0.04016689594849927,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8513761467889909,0.0152512537736609,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03214952147802747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8284313725490197,0.026460569561240675,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8481012658227848,0.023363878096632425,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_human_aging,5,lm-eval,vllm,,acc,none,0.7668161434977578,0.02838039114709467,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_human_sexuality,5,lm-eval,vllm,,acc,none,0.8244274809160306,0.03336820338476075,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_humanities,5,lm-eval,vllm,yes,acc,none,0.6187035069075452,0.006660351037377531,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_international_law,5,lm-eval,vllm,,acc,none,0.859504132231405,0.03172233426002156,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_jurisprudence,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.038935425188248496,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_marketing,5,lm-eval,vllm,,acc,none,0.8846153846153846,0.0209301931851793,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_miscellaneous,5,lm-eval,vllm,,acc,none,0.776500638569604,0.014897235229450705,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_moral_disputes,5,lm-eval,vllm,,acc,none,0.7312138728323699,0.02386800326250009,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_moral_scenarios,5,lm-eval,vllm,,acc,none,0.43798882681564244,0.016593394227564975,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_nutrition,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.02428861946604616,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_other,5,lm-eval,vllm,yes,acc,none,0.7051818474412617,0.007888232245273913,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_philosophy,5,lm-eval,vllm,,acc,none,0.7620578778135049,0.02418515064781868,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_prehistory,5,lm-eval,vllm,,acc,none,0.7993827160493827,0.022282313949774837,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_professional_accounting,5,lm-eval,vllm,,acc,none,0.46099290780141844,0.029736592526424455,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_professional_law,5,lm-eval,vllm,,acc,none,0.4804432855280313,0.012760464028289155,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_professional_medicine,5,lm-eval,vllm,,acc,none,0.6801470588235294,0.028332959514031246,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_professional_psychology,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.01791797406959478,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_public_relations,5,lm-eval,vllm,,acc,none,0.7181818181818181,0.043091187099464606,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_security_studies,5,lm-eval,vllm,,acc,none,0.8040816326530612,0.025409301953225705,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7920051998700033,0.0072077044661685895,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_sociology,5,lm-eval,vllm,,acc,none,0.8258706467661692,0.026814951200421624,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_stem,5,lm-eval,vllm,yes,acc,none,0.6692039327624485,0.008109144577380928,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_sv_world_religions,5,lm-eval,vllm,,acc,none,0.8538011695906432,0.02709729011807083,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4fe1b520b0_2026-10-08T18-00-47.326286.json,1791482086.300089,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr,5,lm-eval,vllm,yes,acc,none,0.641504059250819,0.0038612467465807885,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_anatomy,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.042446332383532265,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_astronomy,5,lm-eval,vllm,,acc,none,0.7631578947368421,0.03459777606810534,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_business_ethics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_college_computer_science,5,lm-eval,vllm,,acc,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_college_medicine,5,lm-eval,vllm,,acc,none,0.6416184971098265,0.0365634365335316,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_computer_security,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6808510638297872,0.03047297336338012,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6689655172413793,0.03921545312467122,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6164021164021164,0.0250437573185202,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_formal_logic,5,lm-eval,vllm,,acc,none,0.5952380952380952,0.043902592653775656,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_global_facts,5,lm-eval,vllm,,acc,none,0.35,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8032258064516129,0.02261640942074208,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6305418719211823,0.03395970381998578,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.793939393939394,0.03158415324047706,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_geography,5,lm-eval,vllm,,acc,none,0.803030303030303,0.02833560973246333,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.7927461139896373,0.02925282329180367,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7102564102564103,0.023000628243688034,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4888888888888889,0.030478009819615792,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7521008403361344,0.028047967224176896,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_physics,5,lm-eval,vllm,,acc,none,0.4966887417218543,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8146788990825689,0.01665927970029582,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6435185185185185,0.03266478331527272,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8088235294117647,0.02759917430064072,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8143459915611815,0.025310495376944835,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_human_aging,5,lm-eval,vllm,,acc,none,0.6860986547085202,0.031146796482972486,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7022900763358778,0.04010358942462197,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_humanities,5,lm-eval,vllm,yes,acc,none,0.5772582359192349,0.006717540325999497,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_international_law,5,lm-eval,vllm,,acc,none,0.8760330578512396,0.030083098716035202,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.0437331304091476,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6687116564417178,0.03697983910025588,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_management,5,lm-eval,vllm,,acc,none,0.7184466019417476,0.044532548363264673,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_medical_genetics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7254150702426565,0.015959829933084018,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7023121387283237,0.024617055388677027,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.32849162011173183,0.01570793539849636,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_nutrition,5,lm-eval,vllm,,acc,none,0.6928104575163399,0.02641560191438905,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_other,5,lm-eval,vllm,yes,acc,none,0.6620534277438043,0.008232728614406897,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_prehistory,5,lm-eval,vllm,,acc,none,0.7623456790123457,0.023683591837008515,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_professional_accounting,5,lm-eval,vllm,,acc,none,0.42907801418439717,0.029525914302558586,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_professional_law,5,lm-eval,vllm,,acc,none,0.4661016949152542,0.012740853872949806,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6617647058823529,0.028739328513983604,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6633986928104575,0.01911721391149511,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_public_relations,5,lm-eval,vllm,,acc,none,0.6090909090909091,0.046737523336702363,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_security_studies,5,lm-eval,vllm,,acc,none,0.7346938775510204,0.028263889943784655,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7354566135846604,0.007857657578596506,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_sociology,5,lm-eval,vllm,,acc,none,0.7960199004975125,0.02849317624532607,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_stem,5,lm-eval,vllm,yes,acc,none,0.6254360926102125,0.008403411281981805,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_tr_world_religions,5,lm-eval,vllm,,acc,none,0.8011695906432749,0.030611116557432514,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e1c6bc5d55_2026-10-08T17-34-56.620736.json,1791480548.1503565,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk,5,lm-eval,vllm,yes,acc,none,0.6609457342258938,0.0038018692194037394,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_abstract_algebra,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_anatomy,5,lm-eval,vllm,,acc,none,0.6370370370370371,0.041539484047424,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7094339622641509,0.027943219989337183,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_college_biology,5,lm-eval,vllm,,acc,none,0.7361111111111112,0.036856510958975304,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_college_chemistry,5,lm-eval,vllm,,acc,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_college_mathematics,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_college_medicine,5,lm-eval,vllm,,acc,none,0.6763005780346821,0.03567603799639168,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_college_physics,5,lm-eval,vllm,,acc,none,0.5490196078431373,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_computer_security,5,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7574468085106383,0.02802022627120023,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6896551724137931,0.03855289616378948,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.656084656084656,0.0244644266255964,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_formal_logic,5,lm-eval,vllm,,acc,none,0.5396825396825397,0.04458029125470974,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_global_facts,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_biology,5,lm-eval,vllm,,acc,none,0.8290322580645161,0.021417242936321575,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.645320197044335,0.03366124489051447,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8606060606060606,0.0270459488258654,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_geography,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026552207828215258,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.717948717948718,0.02281581309889655,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8513761467889909,0.0152512537736609,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.031919234456861886,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7941176470588235,0.028379449451588684,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_human_aging,5,lm-eval,vllm,,acc,none,0.7040358744394619,0.03063659134869978,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_human_sexuality,5,lm-eval,vllm,,acc,none,0.7099236641221374,0.03980066246467765,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_humanities,5,lm-eval,vllm,yes,acc,none,0.5808714133900106,0.0067391714583608965,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7055214723926381,0.03581165790474083,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_machine_learning,5,lm-eval,vllm,,acc,none,0.4642857142857143,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_miscellaneous,5,lm-eval,vllm,,acc,none,0.7203065134099617,0.016050792148036532,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_moral_disputes,5,lm-eval,vllm,,acc,none,0.7254335260115607,0.02402774515526503,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3340782122905028,0.015774911422381653,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_nutrition,5,lm-eval,vllm,,acc,none,0.7516339869281046,0.02473998135511354,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_other,5,lm-eval,vllm,yes,acc,none,0.6807209526874799,0.008174864175342333,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_philosophy,5,lm-eval,vllm,,acc,none,0.6913183279742765,0.026236965881153203,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_prehistory,5,lm-eval,vllm,,acc,none,0.7191358024691358,0.025006469755799246,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_professional_accounting,5,lm-eval,vllm,,acc,none,0.4645390070921986,0.029752389657427127,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_professional_law,5,lm-eval,vllm,,acc,none,0.4817470664928292,0.012761723960595358,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_professional_medicine,5,lm-eval,vllm,,acc,none,0.6727941176470589,0.028501452860396626,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_professional_psychology,5,lm-eval,vllm,,acc,none,0.6977124183006536,0.018579232711113967,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_security_studies,5,lm-eval,vllm,,acc,none,0.7714285714285715,0.026882144922307713,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7663308417289568,0.007483510379377418,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_sociology,5,lm-eval,vllm,,acc,none,0.8407960199004975,0.025870646766169153,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_stem,5,lm-eval,vllm,yes,acc,none,0.6581033935934031,0.008205252374118578,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_mmlu_full_uk_world_religions,5,lm-eval,vllm,,acc,none,0.783625730994152,0.03158149539338735,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/69ef463bca_2026-10-08T17-40-06.480218.json,1791480849.8260996,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5dfa9c91fe_2026-10-08T17-43-56.107703.json,1791481259.9499898,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_bytes,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5dfa9c91fe_2026-10-08T17-43-56.107703.json,1791481259.9499898,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5dfa9c91fe_2026-10-08T17-43-56.107703.json,1791481259.9499898,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fa9349314d_2026-10-08T17-50-43.096863.json,1791481665.0999985,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fa9349314d_2026-10-08T17-50-43.096863.json,1791481665.0999985,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_norm,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fa9349314d_2026-10-08T17-50-43.096863.json,1791481665.0999985,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c099132517_2026-10-08T17-39-00.800760.json,1791480977.7181325,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c099132517_2026-10-08T17-39-00.800760.json,1791480977.7181325,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c099132517_2026-10-08T17-39-00.800760.json,1791480977.7181325,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/acbc6035a1_2026-10-08T17-34-34.515951.json,1791480696.6736093,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/acbc6035a1_2026-10-08T17-34-34.515951.json,1791480696.6736093,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/acbc6035a1_2026-10-08T17-34-34.515951.json,1791480696.6736093,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/49149eee60_2026-10-08T17-37-10.841046.json,1791480850.7513063,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_bytes,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/49149eee60_2026-10-08T17-37-10.841046.json,1791480850.7513063,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/49149eee60_2026-10-08T17-37-10.841046.json,1791480850.7513063,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9cae09e57f_2026-10-08T17-57-49.044333.json,1791482094.2100306,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9cae09e57f_2026-10-08T17-57-49.044333.json,1791482094.2100306,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9cae09e57f_2026-10-08T17-57-49.044333.json,1791482094.2100306,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/06c2551521_2026-10-08T17-41-32.396052.json,1791481113.9302814,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/06c2551521_2026-10-08T17-41-32.396052.json,1791481113.9302814,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_norm,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/06c2551521_2026-10-08T17-41-32.396052.json,1791481113.9302814,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc,none,0.55,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a06b1f1a8c_2026-10-08T17-55-23.437609.json,1791481948.4859693,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_bytes,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a06b1f1a8c_2026-10-08T17-55-23.437609.json,1791481948.4859693,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_norm,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a06b1f1a8c_2026-10-08T17-55-23.437609.json,1791481948.4859693,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e7bf0a908a_2026-10-08T17-50-47.969932.json,1791481668.53864,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_bytes,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e7bf0a908a_2026-10-08T17-50-47.969932.json,1791481668.53864,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e7bf0a908a_2026-10-08T17-50-47.969932.json,1791481668.53864,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/452e73f351_2026-10-08T17-34-32.366084.json,1791480698.4320407,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_bytes,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/452e73f351_2026-10-08T17-34-32.366084.json,1791480698.4320407,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/452e73f351_2026-10-08T17-34-32.366084.json,1791480698.4320407,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6619e86745_2026-10-08T17-57-41.762138.json,1791482085.0547168,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6619e86745_2026-10-08T17-57-41.762138.json,1791482085.0547168,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_norm,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6619e86745_2026-10-08T17-57-41.762138.json,1791482085.0547168,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1a933c71b4_2026-10-08T18-14-14.151223.json,1791483083.724869,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1a933c71b4_2026-10-08T18-14-14.151223.json,1791483083.724869,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1a933c71b4_2026-10-08T18-14-14.151223.json,1791483083.724869,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bbbe744b27_2026-10-08T17-52-57.793449.json,1791481801.8983366,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bbbe744b27_2026-10-08T17-52-57.793449.json,1791481801.8983366,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bbbe744b27_2026-10-08T17-52-57.793449.json,1791481801.8983366,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/42c5302cce_2026-10-08T18-02-34.198626.json,1791482375.3541913,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/42c5302cce_2026-10-08T18-02-34.198626.json,1791482375.3541913,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/42c5302cce_2026-10-08T18-02-34.198626.json,1791482375.3541913,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/41d347586e_2026-10-08T17-34-28.171877.json,1791480694.3925729,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_bytes,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/41d347586e_2026-10-08T17-34-28.171877.json,1791480694.3925729,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_norm,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/41d347586e_2026-10-08T17-34-28.171877.json,1791480694.3925729,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1369ad6881_2026-10-08T17-39-14.216705.json,1791480980.5285125,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_bytes,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1369ad6881_2026-10-08T17-39-14.216705.json,1791480980.5285125,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1369ad6881_2026-10-08T17-39-14.216705.json,1791480980.5285125,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc,none,0.57,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b46b2b304e_2026-10-08T17-34-30.462595.json,1791480696.8172019,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_bytes,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b46b2b304e_2026-10-08T17-34-30.462595.json,1791480696.8172019,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_norm,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b46b2b304e_2026-10-08T17-34-30.462595.json,1791480696.8172019,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6adfea24fb_2026-10-08T17-39-11.374337.json,1791480980.0094278,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_bytes,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6adfea24fb_2026-10-08T17-39-11.374337.json,1791480980.0094278,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6adfea24fb_2026-10-08T17-39-11.374337.json,1791480980.0094278,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f4ba20aa0_2026-10-08T18-05-01.803204.json,1791482519.015945,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f4ba20aa0_2026-10-08T18-05-01.803204.json,1791482519.015945,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f4ba20aa0_2026-10-08T18-05-01.803204.json,1791482519.015945,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/748493dced_2026-10-08T17-55-24.571033.json,1791481944.8452234,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/748493dced_2026-10-08T17-55-24.571033.json,1791481944.8452234,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/748493dced_2026-10-08T17-55-24.571033.json,1791481944.8452234,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/90dbd61916_2026-10-08T17-48-22.689671.json,1791481519.856259,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_bytes,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/90dbd61916_2026-10-08T17-48-22.689671.json,1791481519.856259,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_norm,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/90dbd61916_2026-10-08T17-48-22.689671.json,1791481519.856259,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e65a9cfcd1_2026-10-08T18-00-14.668195.json,1791482235.8379018,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e65a9cfcd1_2026-10-08T18-00-14.668195.json,1791482235.8379018,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_norm,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e65a9cfcd1_2026-10-08T18-00-14.668195.json,1791482235.8379018,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4f477352b4_2026-10-08T17-34-28.452865.json,1791480693.9977999,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4f477352b4_2026-10-08T17-34-28.452865.json,1791480693.9977999,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4f477352b4_2026-10-08T17-34-28.452865.json,1791480693.9977999,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a7aec8ca9_2026-10-08T17-39-08.357555.json,1791480977.5513003,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_bytes,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a7aec8ca9_2026-10-08T17-39-08.357555.json,1791480977.5513003,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a7aec8ca9_2026-10-08T17-39-08.357555.json,1791480977.5513003,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/17bee75aa7_2026-10-08T18-09-33.313620.json,1791482798.3074577,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/17bee75aa7_2026-10-08T18-09-33.313620.json,1791482798.3074577,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/17bee75aa7_2026-10-08T18-09-33.313620.json,1791482798.3074577,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d58f14b24c_2026-10-08T18-05-00.663607.json,1791482517.8255904,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_bytes,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d58f14b24c_2026-10-08T18-05-00.663607.json,1791482517.8255904,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d58f14b24c_2026-10-08T18-05-00.663607.json,1791482517.8255904,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3f0e285a06_2026-10-08T17-41-35.378354.json,1791481114.8633869,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3f0e285a06_2026-10-08T17-41-35.378354.json,1791481114.8633869,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3f0e285a06_2026-10-08T17-41-35.378354.json,1791481114.8633869,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/803ae4891c_2026-10-08T17-37-01.737876.json,1791480849.266986,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/803ae4891c_2026-10-08T17-37-01.737876.json,1791480849.266986,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/803ae4891c_2026-10-08T17-37-01.737876.json,1791480849.266986,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc,none,0.91,0.028762349126466136,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/277a164834_2026-10-08T18-05-01.405340.json,1791482520.350583,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/277a164834_2026-10-08T18-05-01.405340.json,1791482520.350583,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_norm,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/277a164834_2026-10-08T18-05-01.405340.json,1791482520.350583,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/be62b866d7_2026-10-08T17-43-51.221740.json,1791481250.84407,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/be62b866d7_2026-10-08T17-43-51.221740.json,1791481250.84407,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_norm,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/be62b866d7_2026-10-08T17-43-51.221740.json,1791481250.84407,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c549fba210_2026-10-08T17-43-45.813045.json,1791481253.8551044,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c549fba210_2026-10-08T17-43-45.813045.json,1791481253.8551044,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c549fba210_2026-10-08T17-43-45.813045.json,1791481253.8551044,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7c92e2c669_2026-10-08T17-41-21.001263.json,1791481114.8867607,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7c92e2c669_2026-10-08T17-41-21.001263.json,1791481114.8867607,1 +v1annealCT_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_norm,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7c92e2c669_2026-10-08T17-41-21.001263.json,1791481114.8867607,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_als_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.049431107042371025,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6ab184dd31_2026-10-08T18-00-12.526713.json,1791482232.4168866,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_bos_latn,0,lm-eval,vllm,,exact_match,strict_match,0.63,0.048523658709391,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d16411127f_2026-10-08T17-50-44.858758.json,1791481665.6401618,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_bul_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d0ac84c248_2026-10-08T17-39-19.002642.json,1791480977.5747297,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_cat_latn,0,lm-eval,vllm,,exact_match,strict_match,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0ea40233ae_2026-10-08T17-50-57.462636.json,1791481675.5934508,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_ces_latn,0,lm-eval,vllm,,exact_match,strict_match,0.34,0.04760952285695235,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ebd344476d_2026-10-08T17-53-05.904407.json,1791481800.510543,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_deu_latn,0,lm-eval,vllm,,exact_match,strict_match,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fd8fd173d6_2026-10-08T17-50-48.071759.json,1791481673.6148038,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_ekk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.34,0.04760952285695236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ea2037852d_2026-10-08T17-34-38.707318.json,1791480694.7993958,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_ell_grek,0,lm-eval,vllm,,exact_match,strict_match,0.44,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6dd871ee90_2026-10-08T18-11-58.150885.json,1791482932.4726837,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_eng_latn,0,lm-eval,vllm,,exact_match,strict_match,0.31,0.04648231987117316,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/afc13dc2b4_2026-10-08T18-00-22.582870.json,1791482235.127411,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_fin_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/044b9f86d7_2026-10-08T18-11-35.611343.json,1791482899.8024232,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_fra_latn_fran,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/214876e494_2026-10-08T17-34-35.947857.json,1791480696.4101696,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_glg_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/708a28d8a7_2026-10-08T17-34-33.450844.json,1791480692.8571763,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_hrv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7e9f059c58_2026-10-08T17-55-20.298250.json,1791481941.381666,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_hun_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cd1cdca9b7_2026-10-08T17-34-39.936411.json,1791480695.7663991,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_isl_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fd5051aa72_2026-10-08T18-07-24.011264.json,1791482660.213786,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_ita_latn,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.049756985195624284,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/16e4638a52_2026-10-08T17-50-47.505531.json,1791481667.184221,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_kat_geor,0,lm-eval,vllm,,exact_match,strict_match,0.24,0.04292346959909281,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f501d583c1_2026-10-08T17-50-55.761197.json,1791481667.1277888,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_lit_latn,0,lm-eval,vllm,,exact_match,strict_match,0.57,0.049756985195624284,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c68b21818d_2026-10-08T17-39-18.325483.json,1791480977.0989177,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_mkd_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.049999999999999996,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b456e76850_2026-10-08T17-48-33.793201.json,1791481519.895357,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_nld_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c740bf4682_2026-10-08T18-07-26.810904.json,1791482661.3646028,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_nno_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4240dca545_2026-10-08T18-05-05.684910.json,1791482530.7746093,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_nob_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ba53ba5ca_2026-10-08T17-53-09.212805.json,1791481808.8998978,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_pol_latn,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.049236596391733084,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/495f0804aa_2026-10-08T17-55-30.178616.json,1791481943.7864525,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_por_latn_port,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5cf5c65b06_2026-10-08T17-32-11.725661.json,1791480549.26313,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_ron_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/880b80f22f_2026-10-08T18-09-38.831734.json,1791482798.2461803,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_slk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/232d0ddd64_2026-10-08T17-36-54.003506.json,1791480836.746908,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_slv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.44,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ca04e27d21_2026-10-08T17-50-49.548371.json,1791481665.8572638,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_spa_latn_spai,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/713a953d16_2026-10-08T18-09-40.625413.json,1791482797.1475139,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_srp_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/eba9aca3fd_2026-10-08T18-00-15.441301.json,1791482232.9611993,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_swe_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.04943110704237102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b16a1c8fe8_2026-10-08T18-05-01.559277.json,1791482516.7026844,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_tur_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9fbdbf143b_2026-10-08T17-34-32.780870.json,1791480695.8674295,1 +v1annealCT_merge3_116k_120k,global_piqa_prompted_ukr_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ea71dfb313_2026-10-08T17-50-55.821126.json,1791481672.2065809,1 +v1annealCT_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,flexible-extract,0.824109173616376,0.010487120635539637,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e9343f6430_2026-10-08T17-35-38.237665.json,1791480697.6167488,1 +v1annealCT_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,strict-match,0.8233510235026535,0.01050486250585457,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e9343f6430_2026-10-08T17-35-38.237665.json,1791480697.6167488,1 +v1annealCT_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc,none,0.6086436964748058,0.004870563921220537,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d9234b2220_2026-10-08T17-52-10.927073.json,1791481671.824988,1 +v1annealCT_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc_norm,none,0.7994423421629158,0.003995992960088483,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d9234b2220_2026-10-08T17-52-10.927073.json,1791481671.824988,1 +v1annealCT_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc,none,0.6319458275243975,0.0048129052790665434,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/570ffef38f_2026-10-08T17-48-10.384010.json,1791481116.0591908,1 +v1annealCT_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc_norm,none,0.8297151961760606,0.0037511461503849522,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/570ffef38f_2026-10-08T17-48-10.384010.json,1791481116.0591908,1 +v1annealCT_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc,none,0.5091738139181413,0.005209152568497946,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cb5e6eca6b_2026-10-08T17-40-37.047688.json,1791480972.8028457,1 +v1annealCT_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc_norm,none,0.6711540549343177,0.004895280022795303,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cb5e6eca6b_2026-10-08T17-40-37.047688.json,1791480972.8028457,1 +v1annealCT_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc,none,0.539817302525524,0.0051671812096159815,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/651ec034d3_2026-10-08T18-10-55.906796.json,1791482798.4613578,1 +v1annealCT_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc_norm,none,0.6982267598065556,0.004758869075432312,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/651ec034d3_2026-10-08T18-10-55.906796.json,1791482798.4613578,1 +v1annealCT_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc,none,0.53800170794193,0.005151239616249467,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d6c6c8646a_2026-10-08T17-56-35.640662.json,1791481945.9155195,1 +v1annealCT_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc_norm,none,0.6902220324508966,0.00477770589477626,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d6c6c8646a_2026-10-08T17-56-35.640662.json,1791481945.9155195,1 +v1annealCT_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc,none,0.5657136761254534,0.005119730576790795,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/76a0620206_2026-10-08T17-35-53.348994.json,1791480700.8851285,1 +v1annealCT_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc_norm,none,0.7365052272242373,0.0045502432101698215,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/76a0620206_2026-10-08T17-35-53.348994.json,1791480700.8851285,1 +v1annealCT_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc,none,0.30361966504592114,0.004779951060642326,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2c497d6b96_2026-10-08T17-49-28.855829.json,1791481524.3036044,1 +v1annealCT_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc_norm,none,0.36002160994057264,0.004989789123360781,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2c497d6b96_2026-10-08T17-49-28.855829.json,1791481524.3036044,1 +v1annealCT_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc,none,0.556007710430499,0.005141909656138637,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6fe5460fc8_2026-10-08T17-33-33.612257.json,1791480549.3643641,1 +v1annealCT_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc_norm,none,0.7247804669094025,0.004622098407794298,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6fe5460fc8_2026-10-08T17-33-33.612257.json,1791480549.3643641,1 +v1annealCT_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc,none,0.4995248653785239,0.005138008504108225,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9705815e0e_2026-10-08T17-56-42.925393.json,1791481941.2319329,1 +v1annealCT_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc_norm,none,0.6609650512089537,0.004864480796570227,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9705815e0e_2026-10-08T17-56-42.925393.json,1791481941.2319329,1 +v1annealCT_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc,none,0.4503783309573418,0.005210397693866956,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8cef6df068_2026-10-08T18-03-58.790934.json,1791482374.806744,1 +v1annealCT_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc_norm,none,0.5848228972475052,0.005160349149554736,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8cef6df068_2026-10-08T18-03-58.790934.json,1791482374.806744,1 +v1annealCT_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc,none,0.5409550745132166,0.0051976039898991525,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a60902d07_2026-10-08T17-56-30.402556.json,1791481940.8915975,1 +v1annealCT_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc_norm,none,0.7070597193516807,0.004746927372084907,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8a60902d07_2026-10-08T17-56-30.402556.json,1791481940.8915975,1 +v1annealCT_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc,none,0.5378305450620615,0.005179932234649402,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4f94849b3a_2026-10-08T17-56-42.175994.json,1791481945.5788162,1 +v1annealCT_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc_norm,none,0.7004856988667026,0.004758928121352323,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4f94849b3a_2026-10-08T17-56-42.175994.json,1791481945.5788162,1 +v1annealCT_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc,none,0.5469715028713836,0.005181927326683522,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bb512450f2_2026-10-08T17-38-28.170362.json,1791480851.8354669,1 +v1annealCT_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc_norm,none,0.7206631270993608,0.004670641044834582,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bb512450f2_2026-10-08T17-38-28.170362.json,1791480851.8354669,1 +v1annealCT_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc,none,0.5174689021092482,0.005197264423937837,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b4295b3e2f_2026-10-08T17-52-17.465976.json,1791481667.3100898,1 +v1annealCT_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc_norm,none,0.6714981070849108,0.004884963985096226,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b4295b3e2f_2026-10-08T17-52-17.465976.json,1791481667.3100898,1 +v1annealCT_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc,none,0.47569847127042697,0.00512814937747382,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0a3a699acb_2026-10-08T17-52-05.472572.json,1791481667.536504,1 +v1annealCT_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc_norm,none,0.614760147601476,0.00499715343393315,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0a3a699acb_2026-10-08T17-52-05.472572.json,1791481667.536504,1 +v1annealCT_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc,none,0.5036511800190496,0.005143852212977867,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/25f0e8e91c_2026-10-08T18-15-41.847360.json,1791483080.074535,1 +v1annealCT_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc_norm,none,0.6589057043073341,0.004877293823430256,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/25f0e8e91c_2026-10-08T18-15-41.847360.json,1791483080.074535,1 +v1annealCT_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc,none,0.5391361543521158,0.005219324753744348,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d814ee2de9_2026-10-08T18-01-32.032869.json,1791482233.8989637,1 +v1annealCT_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc_norm,none,0.7052181539136154,0.004774093067858808,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d814ee2de9_2026-10-08T18-01-32.032869.json,1791482233.8989637,1 +v1annealCT_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc,none,0.4708258050802423,0.0051461305962651515,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2330e7973a_2026-10-08T17-49-39.133962.json,1791481518.580948,1 +v1annealCT_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc_norm,none,0.608141141460304,0.0050329008258834605,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2330e7973a_2026-10-08T17-49-39.133962.json,1791481518.580948,1 +v1annealCT_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_loose_acc,none,0.45323741007194246,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e11e7507d8_2026-10-08T17-33-48.889628.json,1791480549.8546247,1 +v1annealCT_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_strict_acc,none,0.4196642685851319,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e11e7507d8_2026-10-08T17-33-48.889628.json,1791480549.8546247,1 +v1annealCT_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_loose_acc,none,0.34011090573012936,0.020386791181835815,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e11e7507d8_2026-10-08T17-33-48.889628.json,1791480549.8546247,1 +v1annealCT_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_strict_acc,none,0.31053604436229204,0.01991200129059118,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e11e7507d8_2026-10-08T17-33-48.889628.json,1791480549.8546247,1 +v1annealCT_merge3_116k_120k,include_base_44_albanian,0,lm-eval,vllm,yes,acc,none,0.7459165154264973,0.018507351558111094,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8587af4871_2026-10-08T18-07-18.005977.json,1791482663.0612867,1 +v1annealCT_merge3_116k_120k,include_base_44_albanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.7668161434977578,0.02838039114709467,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8587af4871_2026-10-08T18-07-18.005977.json,1791482663.0612867,1 +v1annealCT_merge3_116k_120k,include_base_44_albanian_business_commerce,0,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8587af4871_2026-10-08T18-07-18.005977.json,1791482663.0612867,1 +v1annealCT_merge3_116k_120k,include_base_44_albanian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8587af4871_2026-10-08T18-07-18.005977.json,1791482663.0612867,1 +v1annealCT_merge3_116k_120k,include_base_44_albanian_social_science,0,lm-eval,vllm,,acc,none,0.8181818181818182,0.0524863881081478,55,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8587af4871_2026-10-08T18-07-18.005977.json,1791482663.0612867,1 +v1annealCT_merge3_116k_120k,include_base_44_albanian_stem,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8587af4871_2026-10-08T18-07-18.005977.json,1791482663.0612867,1 +v1annealCT_merge3_116k_120k,include_base_44_basque,0,lm-eval,vllm,yes,acc,none,0.452,0.022279694107843542,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4ab63bb323_2026-10-08T18-11-53.741102.json,1791482935.945875,1 +v1annealCT_merge3_116k_120k,include_base_44_basque_professional_certification,0,lm-eval,vllm,,acc,none,0.452,0.022279694107843542,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4ab63bb323_2026-10-08T18-11-53.741102.json,1791482935.945875,1 +v1annealCT_merge3_116k_120k,include_base_44_bulgarian,0,lm-eval,vllm,yes,acc,none,0.6872727272727273,0.019635366436371305,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/96d739b624_2026-10-08T17-34-26.191855.json,1791480693.4953408,1 +v1annealCT_merge3_116k_120k,include_base_44_bulgarian_arts_humanities,0,lm-eval,vllm,,acc,none,0.756,0.02721799546455311,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/96d739b624_2026-10-08T17-34-26.191855.json,1791480693.4953408,1 +v1annealCT_merge3_116k_120k,include_base_44_bulgarian_social_science,0,lm-eval,vllm,,acc,none,0.636,0.030491555220405475,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/96d739b624_2026-10-08T17-34-26.191855.json,1791480693.4953408,1 +v1annealCT_merge3_116k_120k,include_base_44_bulgarian_stem,0,lm-eval,vllm,,acc,none,0.6,0.06998542122237651,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/96d739b624_2026-10-08T17-34-26.191855.json,1791480693.4953408,1 +v1annealCT_merge3_116k_120k,include_base_44_croatian,0,lm-eval,vllm,yes,acc,none,0.7363636363636363,0.018746846169856696,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8f838af08c_2026-10-08T17-34-30.630725.json,1791480697.876396,1 +v1annealCT_merge3_116k_120k,include_base_44_croatian_arts_humanities,0,lm-eval,vllm,,acc,none,0.696,0.029150213374159652,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8f838af08c_2026-10-08T17-34-30.630725.json,1791480697.876396,1 +v1annealCT_merge3_116k_120k,include_base_44_croatian_social_science,0,lm-eval,vllm,,acc,none,0.784,0.02607865766373279,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8f838af08c_2026-10-08T17-34-30.630725.json,1791480697.876396,1 +v1annealCT_merge3_116k_120k,include_base_44_croatian_stem,0,lm-eval,vllm,,acc,none,0.7,0.06546536707079771,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8f838af08c_2026-10-08T17-34-30.630725.json,1791480697.876396,1 +v1annealCT_merge3_116k_120k,include_base_44_dutch,0,lm-eval,vllm,yes,acc,none,0.705989110707804,0.01943144455927955,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/193c806a73_2026-10-08T17-55-13.549194.json,1791481943.289625,1 +v1annealCT_merge3_116k_120k,include_base_44_dutch_applied_science,0,lm-eval,vllm,,acc,none,0.8666666666666667,0.09085135251589958,15,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/193c806a73_2026-10-08T17-55-13.549194.json,1791481943.289625,1 +v1annealCT_merge3_116k_120k,include_base_44_dutch_arts_humanities,0,lm-eval,vllm,,acc,none,0.7119341563786008,0.029111066408470707,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/193c806a73_2026-10-08T17-55-13.549194.json,1791481943.289625,1 +v1annealCT_merge3_116k_120k,include_base_44_dutch_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/193c806a73_2026-10-08T17-55-13.549194.json,1791481943.289625,1 +v1annealCT_merge3_116k_120k,include_base_44_dutch_social_science,0,lm-eval,vllm,,acc,none,0.6954732510288066,0.029583207218060927,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/193c806a73_2026-10-08T17-55-13.549194.json,1791481943.289625,1 +v1annealCT_merge3_116k_120k,include_base_44_dutch_stem,0,lm-eval,vllm,,acc,none,0.76,0.08717797887081347,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/193c806a73_2026-10-08T17-55-13.549194.json,1791481943.289625,1 +v1annealCT_merge3_116k_120k,include_base_44_estonian,0,lm-eval,vllm,yes,acc,none,0.6517857142857143,0.031582037404518384,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ae57242cd5_2026-10-08T17-37-01.869307.json,1791480849.212776,1 +v1annealCT_merge3_116k_120k,include_base_44_estonian_applied_science,0,lm-eval,vllm,,acc,none,0.7142857142857143,0.12529400275814703,14,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ae57242cd5_2026-10-08T17-37-01.869307.json,1791480849.212776,1 +v1annealCT_merge3_116k_120k,include_base_44_estonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6211180124223602,0.03835120818393935,161,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ae57242cd5_2026-10-08T17-37-01.869307.json,1791480849.212776,1 +v1annealCT_merge3_116k_120k,include_base_44_estonian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.0,0.0,2,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ae57242cd5_2026-10-08T17-37-01.869307.json,1791480849.212776,1 +v1annealCT_merge3_116k_120k,include_base_44_estonian_social_science,0,lm-eval,vllm,,acc,none,0.6363636363636364,0.15212000482437738,11,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ae57242cd5_2026-10-08T17-37-01.869307.json,1791480849.212776,1 +v1annealCT_merge3_116k_120k,include_base_44_estonian_stem,0,lm-eval,vllm,,acc,none,0.8055555555555556,0.0668977476599572,36,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ae57242cd5_2026-10-08T17-37-01.869307.json,1791480849.212776,1 +v1annealCT_merge3_116k_120k,include_base_44_finnish,0,lm-eval,vllm,yes,acc,none,0.5607985480943739,0.02117254425026811,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/01c189eac5_2026-10-08T17-37-01.772133.json,1791480842.8926907,1 +v1annealCT_merge3_116k_120k,include_base_44_finnish_applied_science,0,lm-eval,vllm,,acc,none,0.5862068965517241,0.0930760769837004,29,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/01c189eac5_2026-10-08T17-37-01.772133.json,1791480842.8926907,1 +v1annealCT_merge3_116k_120k,include_base_44_finnish_arts_humanities,0,lm-eval,vllm,,acc,none,0.5221238938053098,0.033300686234029694,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/01c189eac5_2026-10-08T17-37-01.772133.json,1791480842.8926907,1 +v1annealCT_merge3_116k_120k,include_base_44_finnish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6444444444444445,0.0721639236343101,45,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/01c189eac5_2026-10-08T17-37-01.772133.json,1791480842.8926907,1 +v1annealCT_merge3_116k_120k,include_base_44_finnish_social_science,0,lm-eval,vllm,,acc,none,0.5707964601769911,0.03299749897771093,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/01c189eac5_2026-10-08T17-37-01.772133.json,1791480842.8926907,1 +v1annealCT_merge3_116k_120k,include_base_44_finnish_stem,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/01c189eac5_2026-10-08T17-37-01.772133.json,1791480842.8926907,1 +v1annealCT_merge3_116k_120k,include_base_44_french,0,lm-eval,vllm,yes,acc,none,0.6062052505966588,0.023452058422185024,419,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ada4ba5ff1_2026-10-08T17-55-21.531061.json,1791481946.7168393,1 +v1annealCT_merge3_116k_120k,include_base_44_french_arts_humanities,0,lm-eval,vllm,,acc,none,0.6766917293233082,0.028732995482397362,266,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ada4ba5ff1_2026-10-08T17-55-21.531061.json,1791481946.7168393,1 +v1annealCT_merge3_116k_120k,include_base_44_french_driving_license,0,lm-eval,vllm,,acc,none,0.425531914893617,0.07289875413448861,47,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ada4ba5ff1_2026-10-08T17-55-21.531061.json,1791481946.7168393,1 +v1annealCT_merge3_116k_120k,include_base_44_french_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5,0.12909944487358055,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ada4ba5ff1_2026-10-08T17-55-21.531061.json,1791481946.7168393,1 +v1annealCT_merge3_116k_120k,include_base_44_french_social_science,0,lm-eval,vllm,,acc,none,0.5540540540540541,0.05817759292339765,74,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ada4ba5ff1_2026-10-08T17-55-21.531061.json,1791481946.7168393,1 +v1annealCT_merge3_116k_120k,include_base_44_french_stem,0,lm-eval,vllm,,acc,none,0.3125,0.11967838846954226,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ada4ba5ff1_2026-10-08T17-55-21.531061.json,1791481946.7168393,1 +v1annealCT_merge3_116k_120k,include_base_44_georgian,0,lm-eval,vllm,yes,acc,none,0.474,0.022352791650914174,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ab304c9b65_2026-10-08T17-44-06.509548.json,1791481257.7329726,1 +v1annealCT_merge3_116k_120k,include_base_44_georgian_arts_humanities,0,lm-eval,vllm,,acc,none,0.474,0.022352791650914174,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ab304c9b65_2026-10-08T17-44-06.509548.json,1791481257.7329726,1 +v1annealCT_merge3_116k_120k,include_base_44_german,0,lm-eval,vllm,yes,acc,none,0.49640287769784175,0.042635569289794055,139,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349267bddc_2026-10-08T17-37-02.583416.json,1791480848.7658126,1 +v1annealCT_merge3_116k_120k,include_base_44_german_driving_license,0,lm-eval,vllm,,acc,none,0.6086956521739131,0.10405096111532161,23,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349267bddc_2026-10-08T17-37-02.583416.json,1791480848.7658126,1 +v1annealCT_merge3_116k_120k,include_base_44_german_social_science,0,lm-eval,vllm,,acc,none,0.4835164835164835,0.052675979523069745,91,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349267bddc_2026-10-08T17-37-02.583416.json,1791480848.7658126,1 +v1annealCT_merge3_116k_120k,include_base_44_german_stem,0,lm-eval,vllm,,acc,none,0.44,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349267bddc_2026-10-08T17-37-02.583416.json,1791480848.7658126,1 +v1annealCT_merge3_116k_120k,include_base_44_greek,0,lm-eval,vllm,yes,acc,none,0.6123188405797102,0.020290379148942498,552,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04f098bad3_2026-10-08T17-43-52.603445.json,1791481254.461755,1 +v1annealCT_merge3_116k_120k,include_base_44_greek_arts_humanities,0,lm-eval,vllm,,acc,none,0.35135135135135137,0.07956541321016079,37,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04f098bad3_2026-10-08T17-43-52.603445.json,1791481254.461755,1 +v1annealCT_merge3_116k_120k,include_base_44_greek_business_commerce,0,lm-eval,vllm,,acc,none,0.8095238095238095,0.04986999410368026,63,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04f098bad3_2026-10-08T17-43-52.603445.json,1791481254.461755,1 +v1annealCT_merge3_116k_120k,include_base_44_greek_health_oriented_education,0,lm-eval,vllm,,acc,none,0.52,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04f098bad3_2026-10-08T17-43-52.603445.json,1791481254.461755,1 +v1annealCT_merge3_116k_120k,include_base_44_greek_medical_license,0,lm-eval,vllm,,acc,none,0.6119402985074627,0.04225498765506595,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04f098bad3_2026-10-08T17-43-52.603445.json,1791481254.461755,1 +v1annealCT_merge3_116k_120k,include_base_44_greek_professional_certification,0,lm-eval,vllm,,acc,none,0.5223880597014925,0.043312014931941,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04f098bad3_2026-10-08T17-43-52.603445.json,1791481254.461755,1 +v1annealCT_merge3_116k_120k,include_base_44_greek_social_science,0,lm-eval,vllm,,acc,none,0.6940298507462687,0.03995791178767271,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04f098bad3_2026-10-08T17-43-52.603445.json,1791481254.461755,1 +v1annealCT_merge3_116k_120k,include_base_44_greek_stem,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04f098bad3_2026-10-08T17-43-52.603445.json,1791481254.461755,1 +v1annealCT_merge3_116k_120k,include_base_44_hungarian,0,lm-eval,vllm,yes,acc,none,0.5218181818181818,0.021307267411692213,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/da5c81eb61_2026-10-08T17-43-45.929811.json,1791481251.2797022,1 +v1annealCT_merge3_116k_120k,include_base_44_hungarian_applied_science,0,lm-eval,vllm,,acc,none,0.49560117302052786,0.02711525782335607,341,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/da5c81eb61_2026-10-08T17-43-45.929811.json,1791481251.2797022,1 +v1annealCT_merge3_116k_120k,include_base_44_hungarian_social_science,0,lm-eval,vllm,,acc,none,0.5597826086956522,0.03669591776834159,184,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/da5c81eb61_2026-10-08T17-43-45.929811.json,1791481251.2797022,1 +v1annealCT_merge3_116k_120k,include_base_44_hungarian_stem,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/da5c81eb61_2026-10-08T17-43-45.929811.json,1791481251.2797022,1 +v1annealCT_merge3_116k_120k,include_base_44_italian,0,lm-eval,vllm,yes,acc,none,0.6916058394160584,0.019627622741926865,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f3f143468_2026-10-08T17-34-29.632208.json,1791480694.9817555,1 +v1annealCT_merge3_116k_120k,include_base_44_italian_applied_science,0,lm-eval,vllm,,acc,none,0.7142857142857143,0.07747516350666292,35,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f3f143468_2026-10-08T17-34-29.632208.json,1791480694.9817555,1 +v1annealCT_merge3_116k_120k,include_base_44_italian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6167664670658682,0.037734455202792304,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f3f143468_2026-10-08T17-34-29.632208.json,1791480694.9817555,1 +v1annealCT_merge3_116k_120k,include_base_44_italian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.8333333333333334,0.11236664374387369,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f3f143468_2026-10-08T17-34-29.632208.json,1791480694.9817555,1 +v1annealCT_merge3_116k_120k,include_base_44_italian_professional_certification,0,lm-eval,vllm,,acc,none,0.6774193548387096,0.03766930374975111,155,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f3f143468_2026-10-08T17-34-29.632208.json,1791480694.9817555,1 +v1annealCT_merge3_116k_120k,include_base_44_italian_social_science,0,lm-eval,vllm,,acc,none,0.7724550898203593,0.03253989433108523,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f3f143468_2026-10-08T17-34-29.632208.json,1791480694.9817555,1 +v1annealCT_merge3_116k_120k,include_base_44_italian_stem,0,lm-eval,vllm,,acc,none,0.5833333333333334,0.1486470975026408,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5f3f143468_2026-10-08T17-34-29.632208.json,1791480694.9817555,1 +v1annealCT_merge3_116k_120k,include_base_44_lithuanian,0,lm-eval,vllm,yes,acc,none,0.6610486891385767,0.020463461208055825,534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349fded9c7_2026-10-08T17-41-28.858025.json,1791481112.9166877,1 +v1annealCT_merge3_116k_120k,include_base_44_lithuanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6567164179104478,0.025980183855500764,335,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349fded9c7_2026-10-08T17-41-28.858025.json,1791481112.9166877,1 +v1annealCT_merge3_116k_120k,include_base_44_lithuanian_business_commerce,0,lm-eval,vllm,,acc,none,0.55,0.07966275068156914,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349fded9c7_2026-10-08T17-41-28.858025.json,1791481112.9166877,1 +v1annealCT_merge3_116k_120k,include_base_44_lithuanian_professional_certification,0,lm-eval,vllm,,acc,none,0.6041666666666666,0.0713322023838232,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349fded9c7_2026-10-08T17-41-28.858025.json,1791481112.9166877,1 +v1annealCT_merge3_116k_120k,include_base_44_lithuanian_social_science,0,lm-eval,vllm,,acc,none,0.7272727272727273,0.05108649881354694,77,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349fded9c7_2026-10-08T17-41-28.858025.json,1791481112.9166877,1 +v1annealCT_merge3_116k_120k,include_base_44_lithuanian_stem,0,lm-eval,vllm,,acc,none,0.7647058823529411,0.07384069581892327,34,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/349fded9c7_2026-10-08T17-41-28.858025.json,1791481112.9166877,1 +v1annealCT_merge3_116k_120k,include_base_44_north macedonian,0,lm-eval,vllm,yes,acc,none,0.8148820326678766,0.016375554908745083,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d794743d1f_2026-10-08T18-02-36.384069.json,1791482374.35892,1 +v1annealCT_merge3_116k_120k,include_base_44_north macedonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.8705357142857143,0.022481011862108984,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d794743d1f_2026-10-08T18-02-36.384069.json,1791482374.35892,1 +v1annealCT_merge3_116k_120k,include_base_44_north macedonian_business_commerce,0,lm-eval,vllm,,acc,none,0.78125,0.027683220663030285,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d794743d1f_2026-10-08T18-02-36.384069.json,1791482374.35892,1 +v1annealCT_merge3_116k_120k,include_base_44_north macedonian_social_science,0,lm-eval,vllm,,acc,none,0.8679245283018868,0.046951599766681604,53,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d794743d1f_2026-10-08T18-02-36.384069.json,1791482374.35892,1 +v1annealCT_merge3_116k_120k,include_base_44_north macedonian_stem,0,lm-eval,vllm,,acc,none,0.66,0.0676726816132972,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d794743d1f_2026-10-08T18-02-36.384069.json,1791482374.35892,1 +v1annealCT_merge3_116k_120k,include_base_44_polish,0,lm-eval,vllm,yes,acc,none,0.5456204379562044,0.021070330384822172,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5c10e43839_2026-10-08T18-07-19.196486.json,1791482664.6121616,1 +v1annealCT_merge3_116k_120k,include_base_44_polish_professional_certification,0,lm-eval,vllm,,acc,none,0.5705645161290323,0.02224839792500223,496,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5c10e43839_2026-10-08T18-07-19.196486.json,1791482664.6121616,1 +v1annealCT_merge3_116k_120k,include_base_44_polish_social_science,0,lm-eval,vllm,,acc,none,0.25,0.25,4,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5c10e43839_2026-10-08T18-07-19.196486.json,1791482664.6121616,1 +v1annealCT_merge3_116k_120k,include_base_44_polish_stem,0,lm-eval,vllm,,acc,none,0.3125,0.06761023307918171,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5c10e43839_2026-10-08T18-07-19.196486.json,1791482664.6121616,1 +v1annealCT_merge3_116k_120k,include_base_44_portuguese,0,lm-eval,vllm,yes,acc,none,0.6025408348457351,0.020569555519014977,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f20d6d3f7c_2026-10-08T18-02-43.566793.json,1791482381.0103617,1 +v1annealCT_merge3_116k_120k,include_base_44_portuguese_applied_science,0,lm-eval,vllm,,acc,none,0.5833333333333334,0.054114509952658096,84,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f20d6d3f7c_2026-10-08T18-02-43.566793.json,1791482381.0103617,1 +v1annealCT_merge3_116k_120k,include_base_44_portuguese_arts_humanities,0,lm-eval,vllm,,acc,none,0.6688311688311688,0.038048475825209836,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f20d6d3f7c_2026-10-08T18-02-43.566793.json,1791482381.0103617,1 +v1annealCT_merge3_116k_120k,include_base_44_portuguese_business_commerce,0,lm-eval,vllm,,acc,none,0.4166666666666667,0.058509124791617455,72,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f20d6d3f7c_2026-10-08T18-02-43.566793.json,1791482381.0103617,1 +v1annealCT_merge3_116k_120k,include_base_44_portuguese_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5967741935483871,0.06280789804452513,62,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f20d6d3f7c_2026-10-08T18-02-43.566793.json,1791482381.0103617,1 +v1annealCT_merge3_116k_120k,include_base_44_portuguese_social_science,0,lm-eval,vllm,,acc,none,0.6688311688311688,0.038048475825209836,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f20d6d3f7c_2026-10-08T18-02-43.566793.json,1791482381.0103617,1 +v1annealCT_merge3_116k_120k,include_base_44_portuguese_stem,0,lm-eval,vllm,,acc,none,0.4,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f20d6d3f7c_2026-10-08T18-02-43.566793.json,1791482381.0103617,1 +v1annealCT_merge3_116k_120k,include_base_44_serbian,0,lm-eval,vllm,yes,acc,none,0.6981818181818182,0.019260382840347826,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cc2c454852_2026-10-08T18-07-22.073842.json,1791482660.181428,1 +v1annealCT_merge3_116k_120k,include_base_44_serbian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6549520766773163,0.02691331371114866,313,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cc2c454852_2026-10-08T18-07-22.073842.json,1791482660.181428,1 +v1annealCT_merge3_116k_120k,include_base_44_serbian_social_science,0,lm-eval,vllm,,acc,none,0.8128342245989305,0.02859945370554896,187,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cc2c454852_2026-10-08T18-07-22.073842.json,1791482660.181428,1 +v1annealCT_merge3_116k_120k,include_base_44_serbian_stem,0,lm-eval,vllm,,acc,none,0.54,0.07119963311072636,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cc2c454852_2026-10-08T18-07-22.073842.json,1791482660.181428,1 +v1annealCT_merge3_116k_120k,include_base_44_spanish,0,lm-eval,vllm,yes,acc,none,0.66,0.020177368686878056,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c4bf1717c7_2026-10-08T17-50-43.425002.json,1791481668.7198775,1 +v1annealCT_merge3_116k_120k,include_base_44_spanish_arts_humanities,0,lm-eval,vllm,,acc,none,0.612,0.030881038748993974,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c4bf1717c7_2026-10-08T17-50-43.425002.json,1791481668.7198775,1 +v1annealCT_merge3_116k_120k,include_base_44_spanish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c4bf1717c7_2026-10-08T17-50-43.425002.json,1791481668.7198775,1 +v1annealCT_merge3_116k_120k,include_base_44_spanish_social_science,0,lm-eval,vllm,,acc,none,0.704,0.028928939388379697,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c4bf1717c7_2026-10-08T17-50-43.425002.json,1791481668.7198775,1 +v1annealCT_merge3_116k_120k,include_base_44_spanish_stem,0,lm-eval,vllm,,acc,none,0.72,0.0916515138991168,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c4bf1717c7_2026-10-08T17-50-43.425002.json,1791481668.7198775,1 +v1annealCT_merge3_116k_120k,include_base_44_turkish,0,lm-eval,vllm,yes,acc,none,0.5784671532846716,0.02057592813872907,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43d9aa0b03_2026-10-08T17-50-44.020919.json,1791481667.8915832,1 +v1annealCT_merge3_116k_120k,include_base_44_turkish_arts_humanities,0,lm-eval,vllm,,acc,none,0.572289156626506,0.03851597683718533,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43d9aa0b03_2026-10-08T17-50-44.020919.json,1791481667.8915832,1 +v1annealCT_merge3_116k_120k,include_base_44_turkish_business_commerce,0,lm-eval,vllm,,acc,none,0.7228915662650602,0.03484331592680584,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43d9aa0b03_2026-10-08T17-50-44.020919.json,1791481667.8915832,1 +v1annealCT_merge3_116k_120k,include_base_44_turkish_social_science,0,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43d9aa0b03_2026-10-08T17-50-44.020919.json,1791481667.8915832,1 +v1annealCT_merge3_116k_120k,include_base_44_turkish_stem,0,lm-eval,vllm,,acc,none,0.32,0.06663945022680343,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43d9aa0b03_2026-10-08T17-50-44.020919.json,1791481667.8915832,1 +v1annealCT_merge3_116k_120k,include_base_44_ukrainian,0,lm-eval,vllm,yes,acc,none,0.6327272727272727,0.020555037247771434,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7f3f331d27_2026-10-08T17-57-46.409985.json,1791482087.854012,1 +v1annealCT_merge3_116k_120k,include_base_44_ukrainian_arts_humanities,0,lm-eval,vllm,,acc,none,0.656,0.03010450339231644,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7f3f331d27_2026-10-08T17-57-46.409985.json,1791482087.854012,1 +v1annealCT_merge3_116k_120k,include_base_44_ukrainian_social_science,0,lm-eval,vllm,,acc,none,0.596,0.03109668818482536,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7f3f331d27_2026-10-08T17-57-46.409985.json,1791482087.854012,1 +v1annealCT_merge3_116k_120k,include_base_44_ukrainian_stem,0,lm-eval,vllm,,acc,none,0.7,0.06546536707079771,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7f3f331d27_2026-10-08T17-57-46.409985.json,1791482087.854012,1 +v1annealCT_merge3_116k_120k,jeopardy,10,lm-eval,vllm,,exact_match,strict-match,0.5333018422295701,0.010845429449117329,2117,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ab2ce215e_2026-10-08T17-48-37.270806.json,1791481524.588979,1 +v1annealCT_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,acc,none,0.7265670483213662,0.006209767598604392,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/168223353f_2026-10-08T17-44-03.838004.json,1791481248.3971674,1 +v1annealCT_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,perplexity,none,3.5099650858315257,0.06874853350248919,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/168223353f_2026-10-08T17-44-03.838004.json,1791481248.3971674,1 +v1annealCT_merge3_116k_120k,mbpp,3,lm-eval,vllm,,pass_at_1,none,0.648,0.021380042385946048,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1b0050a644_2026-10-08T17-42-11.765085.json,1791481116.7874217,1 +v1annealCT_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.712,0.028697004587398215,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b6fe1fc654_2026-10-08T17-44-11.538827.json,1791481257.1426272,1 +v1annealCT_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,strict-match,0.776,0.026421361687347905,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b6fe1fc654_2026-10-08T17-44-11.538827.json,1791481257.1426272,1 +v1annealCT_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.844,0.022995023034068744,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fd22794b0b_2026-10-08T17-41-22.108842.json,1791481111.905743,1 +v1annealCT_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,strict-match,0.796,0.02553712157454815,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fd22794b0b_2026-10-08T17-41-22.108842.json,1791481111.905743,1 +v1annealCT_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.84,0.023232714782060664,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/aa38f4479b_2026-10-08T18-05-04.216190.json,1791482517.2640336,1 +v1annealCT_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,strict-match,0.776,0.026421361687347905,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/aa38f4479b_2026-10-08T18-05-04.216190.json,1791482517.2640336,1 +v1annealCT_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.664,0.02993325909419152,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/09b01b9929_2026-10-08T17-55-31.525307.json,1791481943.281513,1 +v1annealCT_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,strict-match,0.744,0.02765710871820491,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/09b01b9929_2026-10-08T17-55-31.525307.json,1791481943.281513,1 +v1annealCT_merge3_116k_120k,mmlu,5,lm-eval,vllm,yes,acc,none,0.7304515026349523,0.003580120317337521,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_abstract_algebra,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_anatomy,5,lm-eval,vllm,,acc,none,0.6222222222222222,0.041883075375958506,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_business_ethics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.769811320754717,0.02590789712240816,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_college_biology,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.031164899666948576,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_college_chemistry,5,lm-eval,vllm,,acc,none,0.55,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_college_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_college_medicine,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.03435568056047877,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_computer_security,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7872340425531915,0.02675439134803978,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_econometrics,5,lm-eval,vllm,,acc,none,0.6403508771929824,0.04514496132873635,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7655172413793103,0.03530625874346591,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6746031746031746,0.02413015829976257,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_formal_logic,5,lm-eval,vllm,,acc,none,0.6587301587301587,0.04240799327574919,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_global_facts,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_biology,5,lm-eval,vllm,,acc,none,0.8806451612903226,0.01844341132531537,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6847290640394089,0.03269080871970192,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8545454545454545,0.02753019635506653,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_geography,5,lm-eval,vllm,,acc,none,0.8838383838383839,0.02282888177524936,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9430051813471503,0.01673108529360757,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7974358974358975,0.020377660970371435,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5074074074074074,0.03048219239519157,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8907563025210085,0.020262987400605306,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_physics,5,lm-eval,vllm,,acc,none,0.6026490066225165,0.03995524007681684,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8899082568807339,0.01341993901868128,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.03114144782353603,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8725490196078431,0.02340553048084634,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8945147679324894,0.019995560723758587,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_human_aging,5,lm-eval,vllm,,acc,none,0.7757847533632287,0.027991534258519482,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_human_sexuality,5,lm-eval,vllm,,acc,none,0.816793893129771,0.03392770926494735,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_humanities,5,lm-eval,vllm,yes,acc,none,0.6826780021253985,0.006480662418813477,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_international_law,5,lm-eval,vllm,,acc,none,0.859504132231405,0.03172233426002156,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_jurisprudence,5,lm-eval,vllm,,acc,none,0.8148148148148148,0.03755265865037181,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_logical_fallacies,5,lm-eval,vllm,,acc,none,0.8282208588957055,0.02963471727237104,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_machine_learning,5,lm-eval,vllm,,acc,none,0.5357142857142857,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_management,5,lm-eval,vllm,,acc,none,0.8058252427184466,0.03916667762822582,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_marketing,5,lm-eval,vllm,,acc,none,0.8760683760683761,0.021586494001281407,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_medical_genetics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_miscellaneous,5,lm-eval,vllm,,acc,none,0.8544061302681992,0.012612475800423417,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_moral_disputes,5,lm-eval,vllm,,acc,none,0.7947976878612717,0.021742519835276364,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5486033519553073,0.01664330737231585,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_nutrition,5,lm-eval,vllm,,acc,none,0.7712418300653595,0.02405102973991231,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_other,5,lm-eval,vllm,yes,acc,none,0.7495976826520759,0.0074826982121363635,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_philosophy,5,lm-eval,vllm,,acc,none,0.7781350482315113,0.023598858292862998,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_prehistory,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.020736358408059978,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_professional_accounting,5,lm-eval,vllm,,acc,none,0.5354609929078015,0.02975238965742713,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_professional_law,5,lm-eval,vllm,,acc,none,0.5541069100391134,0.01269524471137965,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_professional_medicine,5,lm-eval,vllm,,acc,none,0.7463235294117647,0.026431329870789562,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_professional_psychology,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.017401816711427615,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8248293792655184,0.00672364503790502,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_sociology,5,lm-eval,vllm,,acc,none,0.8805970149253731,0.022928793277219726,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_stem,5,lm-eval,vllm,yes,acc,none,0.6907706945765937,0.007954625595237356,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,mmlu_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/43f8d881e1_2026-10-08T17-55-56.333552.json,1791481801.1911848,1 +v1annealCT_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc,none,0.9816924328722538,0.002704583916430235,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4ee99a4bd3_2026-10-08T17-41-26.721410.json,1791481120.317569,1 +v1annealCT_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc_norm,none,0.9755899104963385,0.0031132626238845732,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4ee99a4bd3_2026-10-08T17-41-26.721410.json,1791481120.317569,1 +v1annealCT_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc,none,0.978984238178634,0.0030019777081959345,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/82b36b9c66_2026-10-08T17-41-25.097678.json,1791481111.0174305,1 +v1annealCT_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc_norm,none,0.978108581436077,0.003062510111164055,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/82b36b9c66_2026-10-08T17-41-25.097678.json,1791481111.0174305,1 +v1annealCT_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc,none,0.9579417293233082,0.0030771273456555877,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b38f824964_2026-10-08T18-07-35.184706.json,1791482660.4368393,1 +v1annealCT_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc_norm,none,0.9607612781954887,0.0029765651272358755,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b38f824964_2026-10-08T18-07-35.184706.json,1791482660.4368393,1 +v1annealCT_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/aaa0798fdb_2026-10-08T17-43-09.932143.json,1791481249.715685,1 +v1annealCT_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/aaa0798fdb_2026-10-08T17-43-09.932143.json,1791481249.715685,1 +v1annealCT_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc,none,0.984769364664926,0.0025553228424341464,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cb5e6bd3ad_2026-10-08T17-57-33.687585.json,1791482089.0739443,1 +v1annealCT_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc_norm,none,0.983899042645779,0.002626156608305116,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cb5e6bd3ad_2026-10-08T17-57-33.687585.json,1791482089.0739443,1 +v1annealCT_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc,none,0.9972627737226277,0.0015788944371116819,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d0dae18178_2026-10-08T17-41-15.930414.json,1791481113.48636,1 +v1annealCT_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc_norm,none,0.9936131386861314,0.0024073838689802887,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d0dae18178_2026-10-08T17-41-15.930414.json,1791481113.48636,1 +v1annealCT_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc,none,0.990909090909091,0.0034226098344796205,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fcc2119ec_2026-10-08T17-54-52.307710.json,1791481940.7696588,1 +v1annealCT_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc_norm,none,0.990909090909091,0.0034226098344796205,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8fcc2119ec_2026-10-08T17-54-52.307710.json,1791481940.7696588,1 +v1annealCT_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc,none,0.9316504854368932,0.004973818727683633,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2de8b5b74f_2026-10-08T17-32-02.545927.json,1791480549.1612258,1 +v1annealCT_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc_norm,none,0.9324271844660195,0.004947538694695123,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2de8b5b74f_2026-10-08T17-32-02.545927.json,1791480549.1612258,1 +v1annealCT_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc,none,0.9816849816849816,0.008130276209750445,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1744d07d1f_2026-10-08T17-38-32.763003.json,1791480973.9449174,1 +v1annealCT_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc_norm,none,0.6996336996336996,0.02779562928312134,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1744d07d1f_2026-10-08T17-38-32.763003.json,1791480973.9449174,1 +v1annealCT_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc,none,0.9517509727626459,0.0042278920836052985,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/08a8f274dd_2026-10-08T17-41-27.471834.json,1791481113.157995,1 +v1annealCT_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc_norm,none,0.9463035019455253,0.004447399603720517,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/08a8f274dd_2026-10-08T17-41-27.471834.json,1791481113.157995,1 +v1annealCT_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc,none,0.9894034536891679,0.002028870879670251,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/11d2a9ef34_2026-10-08T17-43-42.773055.json,1791481251.9705603,1 +v1annealCT_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc_norm,none,0.9858712715855573,0.0023385527563100634,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/11d2a9ef34_2026-10-08T17-43-42.773055.json,1791481251.9705603,1 +v1annealCT_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.06734350297014738,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d996091b45_2026-10-08T18-02-15.401464.json,1791482374.5857046,1 +v1annealCT_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc_norm,none,0.75,0.08333333333333333,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d996091b45_2026-10-08T18-02-15.401464.json,1791482374.5857046,1 +v1annealCT_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc,none,0.9721115537848606,0.006004284904235447,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d99a492a84_2026-10-08T17-38-53.668103.json,1791480983.124185,1 +v1annealCT_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc_norm,none,0.9548472775564409,0.007571815222957024,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d99a492a84_2026-10-08T17-38-53.668103.json,1791480983.124185,1 +v1annealCT_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc,none,0.9847839318320146,0.002135767691941217,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/afb4407e25_2026-10-08T18-09-45.170651.json,1791482796.8905454,1 +v1annealCT_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc_norm,none,0.9838709677419355,0.0021978879149311863,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/afb4407e25_2026-10-08T18-09-45.170651.json,1791482796.8905454,1 +v1annealCT_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc,none,0.9857988165680474,0.004072725984449868,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f358e5139d_2026-10-08T17-50-24.103089.json,1791481667.7232845,1 +v1annealCT_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc_norm,none,0.9822485207100592,0.004545239198936023,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f358e5139d_2026-10-08T17-50-24.103089.json,1791481667.7232845,1 +v1annealCT_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc,none,0.979293109603713,0.0026911306098793704,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/971c48fe8b_2026-10-08T18-02-39.597683.json,1791482374.2713852,1 +v1annealCT_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc_norm,none,0.97036772581221,0.003204583910713443,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/971c48fe8b_2026-10-08T18-02-39.597683.json,1791482374.2713852,1 +v1annealCT_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc,none,0.9639879959986662,0.003402856566414208,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e97d5d4968_2026-10-08T17-55-21.508238.json,1791481943.816509,1 +v1annealCT_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc_norm,none,0.9506502167389129,0.0039558260524904226,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e97d5d4968_2026-10-08T17-55-21.508238.json,1791481943.816509,1 +v1annealCT_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc,none,0.946078431372549,0.015852465281106905,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ef4c65257_2026-10-08T18-00-01.518296.json,1791482240.2570364,1 +v1annealCT_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc_norm,none,0.9019607843137255,0.02087111845555211,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2ef4c65257_2026-10-08T18-00-01.518296.json,1791482240.2570364,1 +v1annealCT_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc,none,0.9597625329815304,0.003569474178972875,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3fe9aa2169_2026-10-08T17-39-23.769476.json,1791480973.9463754,1 +v1annealCT_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc_norm,none,0.962401055408971,0.003455197718757583,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3fe9aa2169_2026-10-08T17-39-23.769476.json,1791480973.9463754,1 +v1annealCT_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc,none,0.9847457627118644,0.003569442634838611,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/56eabab507_2026-10-08T17-34-14.693629.json,1791480698.694819,1 +v1annealCT_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc_norm,none,0.9771186440677966,0.004354693828507355,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/56eabab507_2026-10-08T17-34-14.693629.json,1791480698.694819,1 +v1annealCT_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7bd92d52a4_2026-10-08T18-08-59.382487.json,1791482794.4838161,1 +v1annealCT_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7bd92d52a4_2026-10-08T18-08-59.382487.json,1791482794.4838161,1 +v1annealCT_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc,none,0.9510939510939511,0.004468019277071009,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1ed7fc13f1_2026-10-08T17-55-08.887415.json,1791481942.3309836,1 +v1annealCT_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc_norm,none,0.9322179322179323,0.005207606646292792,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1ed7fc13f1_2026-10-08T17-55-08.887415.json,1791481942.3309836,1 +v1annealCT_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc,none,0.9706601466992665,0.0029506812456133913,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/857df14e7e_2026-10-08T18-05-02.179296.json,1791482519.6388435,1 +v1annealCT_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc_norm,none,0.9483496332518337,0.003869730077433552,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/857df14e7e_2026-10-08T18-05-02.179296.json,1791482519.6388435,1 +v1annealCT_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc,none,0.9724409448818898,0.0029657022925976134,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a3426bb70d_2026-10-08T17-50-44.250530.json,1791481669.908574,1 +v1annealCT_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc_norm,none,0.9701443569553806,0.0030831536511868726,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a3426bb70d_2026-10-08T17-50-44.250530.json,1791481669.908574,1 +v1annealCT_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc,none,0.9771400778210116,0.003296931120174067,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/133a764c78_2026-10-08T17-34-21.825326.json,1791480693.500586,1 +v1annealCT_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc_norm,none,0.9688715953307393,0.0038309424740420837,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/133a764c78_2026-10-08T17-34-21.825326.json,1791480693.500586,1 +v1annealCT_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc,none,0.9471652593486127,0.0034750639154037,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/75973ce28a_2026-10-08T17-39-18.885065.json,1791480980.395267,1 +v1annealCT_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc_norm,none,0.9519903498190591,0.0033210137247316994,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/75973ce28a_2026-10-08T17-39-18.885065.json,1791480980.395267,1 +v1annealCT_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc,none,0.9444568369395494,0.0034211367597077372,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bb8c059753_2026-10-08T17-37-22.958175.json,1791480848.5817716,1 +v1annealCT_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc_norm,none,0.9346419808164176,0.003691782924063542,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bb8c059753_2026-10-08T17-37-22.958175.json,1791480848.5817716,1 +v1annealCT_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc,none,0.977961432506887,0.0029129678182606526,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0b9aea8983_2026-10-08T18-11-54.333438.json,1791482932.0167544,1 +v1annealCT_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc_norm,none,0.9795356158992523,0.0028092642775558686,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0b9aea8983_2026-10-08T18-11-54.333438.json,1791482932.0167544,1 +v1annealCT_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc,none,0.9753086419753086,0.009975526843227372,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c7d78c19fa_2026-10-08T17-31-46.046893.json,1791480549.3393574,1 +v1annealCT_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc_norm,none,0.9670781893004116,0.011470040940333626,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c7d78c19fa_2026-10-08T17-31-46.046893.json,1791480549.3393574,1 +v1annealCT_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc,none,0.9950248756218906,0.004975124378109453,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bab899eb5d_2026-10-08T18-06-53.188593.json,1791482666.617566,1 +v1annealCT_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc_norm,none,0.9950248756218906,0.004975124378109453,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/bab899eb5d_2026-10-08T18-06-53.188593.json,1791482666.617566,1 +v1annealCT_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc,none,0.9357060849598163,0.005878347789428622,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e3754fbec5_2026-10-08T17-57-43.632834.json,1791482095.9827633,1 +v1annealCT_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc_norm,none,0.8765786452353617,0.007882994294924957,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e3754fbec5_2026-10-08T17-57-43.632834.json,1791482095.9827633,1 +v1annealCT_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc,none,0.9795918367346939,0.0026996759326348425,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/71a4e6d66d_2026-10-08T17-37-00.455221.json,1791480840.9925005,1 +v1annealCT_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc_norm,none,0.9733965014577259,0.0030725670099238213,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/71a4e6d66d_2026-10-08T17-37-00.455221.json,1791480840.9925005,1 +v1annealCT_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc,none,0.338,0.021175665695209452,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1276db7e64_2026-10-08T18-04-58.915446.json,1791482517.0939405,1 +v1annealCT_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc_norm,none,0.474,0.022352791650914174,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1276db7e64_2026-10-08T18-04-58.915446.json,1791482517.0939405,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,bleu,none,18.034995819110385,0.28756431399655785,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/291a9ebf46_2026-10-08T18-02-09.676259.json,1791482233.8214092,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,chrf,none,37.5728432610609,0.28908706834764425,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/291a9ebf46_2026-10-08T18-02-09.676259.json,1791482233.8214092,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,bleu,none,23.632190896282772,0.2887711069040718,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/db258b1824_2026-10-08T17-43-24.703419.json,1791481111.5256424,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,chrf,none,41.87632800453977,0.2698106483769998,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/db258b1824_2026-10-08T17-43-24.703419.json,1791481111.5256424,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,bleu,none,30.399032150683546,0.33098385819872955,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/61e5773068_2026-10-08T17-34-15.320962.json,1791480552.5180938,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,chrf,none,49.5373717017011,0.2856540070821412,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/61e5773068_2026-10-08T17-34-15.320962.json,1791480552.5180938,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,bleu,none,28.665283999907352,0.3015892126034262,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5057cf9005_2026-10-08T17-36-10.828443.json,1791480693.996924,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,chrf,none,49.08825109609456,0.25873625148633483,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5057cf9005_2026-10-08T17-36-10.828443.json,1791480693.996924,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,bleu,none,29.43571093808711,0.3571055267250572,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fd95de2e49_2026-10-08T17-41-06.585303.json,1791480973.80074,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,chrf,none,47.543811304893666,0.30909967321688825,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fd95de2e49_2026-10-08T17-41-06.585303.json,1791480973.80074,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,bleu,none,13.71752347243012,0.2669439364192613,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f96750c15b_2026-10-08T17-52-45.430414.json,1791481667.2309294,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,chrf,none,39.21979938994843,0.28700146404871935,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f96750c15b_2026-10-08T17-52-45.430414.json,1791481667.2309294,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,bleu,none,17.783237573739793,0.3049630218299295,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4d4ee85e33_2026-10-08T17-59-42.617988.json,1791482085.3843167,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,chrf,none,40.510037897806875,0.24844378215856044,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4d4ee85e33_2026-10-08T17-59-42.617988.json,1791482085.3843167,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,bleu,none,30.030337294440496,0.32612537529074576,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/75248417f6_2026-10-08T17-57-25.253255.json,1791481942.2121372,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,chrf,none,52.21948816713209,0.24504030627027826,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/75248417f6_2026-10-08T17-57-25.253255.json,1791481942.2121372,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,bleu,none,24.33373728263265,0.3038524298142659,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/66d6b597b1_2026-10-08T17-46-04.371049.json,1791481256.1007926,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,chrf,none,49.51858062230595,0.28435832641163916,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/66d6b597b1_2026-10-08T17-46-04.371049.json,1791481256.1007926,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,bleu,none,24.435217059463604,0.35420189821998904,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1b437a110d_2026-10-08T18-04-58.526201.json,1791482374.555641,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,chrf,none,48.077905293463466,0.3147481418212093,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1b437a110d_2026-10-08T18-04-58.526201.json,1791482374.555641,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,bleu,none,30.074466356874005,0.3370211191136085,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cb5b3d6326_2026-10-08T18-02-17.015616.json,1791482238.2056127,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,chrf,none,52.91987563243242,0.28628912233995535,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cb5b3d6326_2026-10-08T18-02-17.015616.json,1791482238.2056127,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,bleu,none,21.836733959375007,0.35674868701197954,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8013f51664_2026-10-08T18-14-00.476796.json,1791482932.7541697,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,chrf,none,45.84138797175361,0.2768252818595074,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8013f51664_2026-10-08T18-14-00.476796.json,1791482932.7541697,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,bleu,none,17.24752120185351,0.3434079106450051,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a5cd65bd45_2026-10-08T17-39-01.679719.json,1791480847.7951927,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,chrf,none,46.66745541355824,0.2618038435767741,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a5cd65bd45_2026-10-08T17-39-01.679719.json,1791480847.7951927,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,bleu,none,16.954113198857016,0.24852717204858774,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/116ea298c2_2026-10-08T17-53-02.481399.json,1791481668.8820326,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,chrf,none,44.61444430242494,0.25879664040924805,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/116ea298c2_2026-10-08T17-53-02.481399.json,1791481668.8820326,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,bleu,none,25.1507052882628,0.3449808655995008,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cbc753f3f3_2026-10-08T17-38-54.475711.json,1791480840.9517207,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,chrf,none,52.167139900120006,0.2884263344035517,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cbc753f3f3_2026-10-08T17-38-54.475711.json,1791480840.9517207,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,bleu,none,17.48152221928047,0.2846646552638545,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/625f946fc8_2026-10-08T18-14-03.874299.json,1791482934.715507,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,chrf,none,40.529998251571,0.25616675485674195,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/625f946fc8_2026-10-08T18-14-03.874299.json,1791482934.715507,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,bleu,none,29.492752114082645,0.320381001932009,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e41e9e0c3f_2026-10-08T17-41-28.898075.json,1791480978.965759,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,chrf,none,52.41388087781874,0.23666263992833375,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e41e9e0c3f_2026-10-08T17-41-28.898075.json,1791480978.965759,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,bleu,none,18.09592720061482,0.29181776282008215,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/705c7a7927_2026-10-08T18-07-16.727874.json,1791482531.879607,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,chrf,none,42.20158419338658,0.26232614725777154,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/705c7a7927_2026-10-08T18-07-16.727874.json,1791482531.879607,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,bleu,none,21.294435451344462,0.3338841858226122,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f986db374a_2026-10-08T17-46-35.933496.json,1791481253.023681,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,chrf,none,44.68800214322378,0.2403339203109128,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f986db374a_2026-10-08T17-46-35.933496.json,1791481253.023681,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,bleu,none,20.657141849621247,0.2795113066226638,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5d97b1fc75_2026-10-08T18-09-12.436157.json,1791482659.2299826,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,chrf,none,47.09400151265327,0.2523733089603976,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5d97b1fc75_2026-10-08T18-09-12.436157.json,1791482659.2299826,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,bleu,none,32.28642107995239,0.31588466248343844,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/370fa614bc_2026-10-08T17-43-32.450978.json,1791481115.4505332,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,chrf,none,56.06131165731079,0.27726721653999997,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/370fa614bc_2026-10-08T17-43-32.450978.json,1791481115.4505332,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,bleu,none,21.0113177411038,0.3291303820151463,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e8fb7a5739_2026-10-08T17-36-28.736569.json,1791480693.8117373,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,chrf,none,45.98832141553638,0.2742116107295068,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e8fb7a5739_2026-10-08T17-36-28.736569.json,1791480693.8117373,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,bleu,none,24.748067922284,0.2915184033157322,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/56662b2a93_2026-10-08T17-34-16.838275.json,1791480552.4173903,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,chrf,none,51.30701958125768,0.2634990024515911,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/56662b2a93_2026-10-08T17-34-16.838275.json,1791480552.4173903,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,bleu,none,26.387216155555798,0.35051330292446264,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9987fc508a_2026-10-08T17-45-55.483959.json,1791481249.9713495,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,chrf,none,51.34432067797312,0.26456536579991924,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9987fc508a_2026-10-08T17-45-55.483959.json,1791481249.9713495,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,bleu,none,24.17523837314704,0.40559325289692844,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/36c1c116f0_2026-10-08T18-11-41.998894.json,1791482797.12723,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,chrf,none,47.12711782135772,0.27751057558863285,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/36c1c116f0_2026-10-08T18-11-41.998894.json,1791482797.12723,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,bleu,none,15.216072229991328,0.27418504930388277,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cf7878f2f9_2026-10-08T17-43-36.282285.json,1791481118.8985713,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,chrf,none,41.182425217301564,0.25566478180816266,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cf7878f2f9_2026-10-08T17-43-36.282285.json,1791481118.8985713,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,bleu,none,7.266543689293453,0.21782572779136772,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2a8d1e9034_2026-10-08T17-36-23.199976.json,1791480695.5451882,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,chrf,none,13.56481585413879,0.3575553109290863,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2a8d1e9034_2026-10-08T17-36-23.199976.json,1791480695.5451882,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,bleu,none,34.940357075802396,0.3427581611536524,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/caa6772157_2026-10-08T17-46-08.120434.json,1791481256.672787,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,chrf,none,55.81679322290456,0.26758104848094183,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/caa6772157_2026-10-08T17-46-08.120434.json,1791481256.672787,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,bleu,none,20.593571662344786,0.31561118446201086,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4cfd6f71f7_2026-10-08T18-09-21.037014.json,1791482662.5298297,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,chrf,none,47.826805057135694,0.28144303799025183,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4cfd6f71f7_2026-10-08T18-09-21.037014.json,1791482662.5298297,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,bleu,none,17.016376845214683,0.28142756905447275,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9d09a3d742_2026-10-08T18-16-37.702852.json,1791483077.2622514,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,chrf,none,38.9199236782785,0.26419056365138127,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9d09a3d742_2026-10-08T18-16-37.702852.json,1791483077.2622514,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,bleu,none,31.936964281681128,0.33132369790868604,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/55dbc7d269_2026-10-08T17-41-17.694026.json,1791480976.8451293,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,chrf,none,50.75328564851074,0.28749553994163063,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/55dbc7d269_2026-10-08T17-41-17.694026.json,1791480976.8451293,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,bleu,none,28.541719399015474,0.3638911305291993,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5b4306a5b1_2026-10-08T17-41-16.456727.json,1791480973.6737797,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,chrf,none,47.0853877669607,0.30874559307145444,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5b4306a5b1_2026-10-08T17-41-16.456727.json,1791480973.6737797,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,bleu,none,23.92907548165529,0.30425748604009933,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7ac69c1658_2026-10-08T17-38-53.631613.json,1791480847.5349736,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,chrf,none,43.91471227748884,0.2639849089957566,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7ac69c1658_2026-10-08T17-38-53.631613.json,1791480847.5349736,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,bleu,none,19.852011679532186,0.28097239268824603,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0d13e95008_2026-10-08T18-09-11.907518.json,1791482665.4231548,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,chrf,none,39.49106683032772,0.2504051248682818,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0d13e95008_2026-10-08T18-09-11.907518.json,1791482665.4231548,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,bleu,none,25.77011893891849,0.4133066762584421,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/dcade1abf1_2026-10-08T17-50-25.239440.json,1791481525.0834608,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,chrf,none,44.433625422078904,0.4057837981018442,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/dcade1abf1_2026-10-08T17-50-25.239440.json,1791481525.0834608,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,bleu,none,23.584085068310497,0.3128885181250026,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1130c5096f_2026-10-08T17-36-27.555487.json,1791480694.3650181,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,chrf,none,42.24126190798418,0.26802520898899046,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1130c5096f_2026-10-08T17-36-27.555487.json,1791480694.3650181,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,bleu,none,32.38052372340085,0.31421809101438253,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1f20d5a1a2_2026-10-08T17-34-16.113852.json,1791480549.2085488,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,chrf,none,50.358652478083954,0.2664222659380552,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1f20d5a1a2_2026-10-08T17-34-16.113852.json,1791480549.2085488,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,bleu,none,24.66620320588242,0.3286414045533505,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/af389dd3c0_2026-10-08T17-52-53.395178.json,1791481667.3757114,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,chrf,none,42.12698709426109,0.31029405768036805,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/af389dd3c0_2026-10-08T17-52-53.395178.json,1791481667.3757114,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,bleu,none,27.79999554705858,0.3603193607642705,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/621faf7a87_2026-10-08T18-04-42.890093.json,1791482381.0494766,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,chrf,none,45.93890850873266,0.33015641874299567,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/621faf7a87_2026-10-08T18-04-42.890093.json,1791482381.0494766,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,bleu,none,23.660752257318237,0.3083909519108875,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/27281a34f7_2026-10-08T18-13-42.009280.json,1791482899.6911862,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,chrf,none,42.99602455767796,0.2544219517307805,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/27281a34f7_2026-10-08T18-13-42.009280.json,1791482899.6911862,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,bleu,none,32.17146435145936,0.3389993086834447,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1bf6d7ecca_2026-10-08T17-45-48.772259.json,1791481253.4399273,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,chrf,none,50.78971328545761,0.2801464154227156,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1bf6d7ecca_2026-10-08T17-45-48.772259.json,1791481253.4399273,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,bleu,none,27.204672340591664,0.31385928729598084,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/06955b38e6_2026-10-08T18-07-16.637232.json,1791482523.267747,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,chrf,none,46.20469999124264,0.25641280268300287,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/06955b38e6_2026-10-08T18-07-16.637232.json,1791482523.267747,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,bleu,none,34.84516759960001,0.35549109379468874,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/567810a9fe_2026-10-08T17-41-09.163638.json,1791480979.6908576,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,chrf,none,53.08100979607347,0.29702712127898423,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/567810a9fe_2026-10-08T17-41-09.163638.json,1791480979.6908576,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,bleu,none,33.70890058981337,0.35805450562986935,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f57d2a603b_2026-10-08T17-41-11.228999.json,1791480973.1121132,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,chrf,none,51.55751303586656,0.2744967810201536,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f57d2a603b_2026-10-08T17-41-11.228999.json,1791480973.1121132,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,bleu,none,30.453957793558878,0.3378424405747383,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/86fc810189_2026-10-08T17-59-45.177899.json,1791482090.2511897,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,chrf,none,47.85030599019281,0.30024374544064053,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/86fc810189_2026-10-08T17-59-45.177899.json,1791482090.2511897,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,bleu,none,19.856022044535848,0.2814246174547592,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/63823c01b9_2026-10-08T17-43-06.692863.json,1791481113.6076038,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,chrf,none,38.66249827061326,0.2596636088729986,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/63823c01b9_2026-10-08T17-43-06.692863.json,1791481113.6076038,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,bleu,none,30.48247334276041,0.3668736389953321,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1b24438b47_2026-10-08T18-13-53.993546.json,1791482933.680782,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,chrf,none,50.59290397690048,0.31762777243812285,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1b24438b47_2026-10-08T18-13-53.993546.json,1791482933.680782,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,bleu,none,38.01937497102955,0.3224771680976892,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/790beddf7f_2026-10-08T17-34-05.344320.json,1791480548.0692475,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,chrf,none,55.14941562808633,0.2786820390617537,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/790beddf7f_2026-10-08T17-34-05.344320.json,1791480548.0692475,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,bleu,none,26.336810078608043,0.32031151741427394,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4a7ea06603_2026-10-08T17-45-50.957719.json,1791481255.0983262,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,chrf,none,45.2635631387024,0.3395324143505992,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4a7ea06603_2026-10-08T17-45-50.957719.json,1791481255.0983262,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,bleu,none,25.100990845001597,0.34770878781989023,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2837436bfb_2026-10-08T17-59-57.946612.json,1791482092.2707312,1 +v1annealCT_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,chrf,none,43.88127080716953,0.2775906252246654,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2837436bfb_2026-10-08T17-59-57.946612.json,1791482092.2707312,1 +v1annealCT_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc,none,0.808487486398259,0.009180802635734005,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/17e6d9273a_2026-10-08T18-11-35.658092.json,1791482899.6142552,1 +v1annealCT_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc_norm,none,0.8144722524483133,0.009069597302603977,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/17e6d9273a_2026-10-08T18-11-35.658092.json,1791482899.6142552,1 +v1annealCT_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc,none,0.8286180631120783,0.00879235355292935,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ab814c2316_2026-10-08T17-37-19.446959.json,1791480843.1596508,1 +v1annealCT_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc_norm,none,0.8400435255712732,0.008552581630162166,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ab814c2316_2026-10-08T17-37-19.446959.json,1791480843.1596508,1 +v1annealCT_merge3_116k_120k,polymath_de_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/20ad74de74_2026-10-08T17-37-23.741819.json,1791480850.68608,1 +v1annealCT_merge3_116k_120k,polymath_de_low,0,lm-eval,vllm,,exact_match,none,0.392,0.04384135623049351,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ec1bc44ae2_2026-10-08T18-02-58.643692.json,1791482374.440996,1 +v1annealCT_merge3_116k_120k,polymath_de_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b764614c48_2026-10-08T17-34-58.606041.json,1791480697.4174821,1 +v1annealCT_merge3_116k_120k,polymath_de_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/221a6a6c08_2026-10-08T18-09-53.082583.json,1791482795.8828824,1 +v1annealCT_merge3_116k_120k,polymath_en_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/333e571463_2026-10-08T17-37-26.512027.json,1791480843.186023,1 +v1annealCT_merge3_116k_120k,polymath_en_low,0,lm-eval,vllm,,exact_match,none,0.176,0.034198660603841996,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7f315fb321_2026-10-08T17-34-56.395466.json,1791480697.8434312,1 +v1annealCT_merge3_116k_120k,polymath_en_medium,0,lm-eval,vllm,,exact_match,none,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6acca011dc_2026-10-08T17-44-11.135344.json,1791481252.7276652,1 +v1annealCT_merge3_116k_120k,polymath_en_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/12cb41a770_2026-10-08T17-37-26.342605.json,1791480848.9291456,1 +v1annealCT_merge3_116k_120k,polymath_es_high,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/19d27fb864_2026-10-08T17-51-06.640537.json,1791481668.321017,1 +v1annealCT_merge3_116k_120k,polymath_es_low,0,lm-eval,vllm,,exact_match,none,0.352,0.04288920459705148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1bb1e90117_2026-10-08T17-39-34.738826.json,1791480977.512545,1 +v1annealCT_merge3_116k_120k,polymath_es_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/839eee26fd_2026-10-08T17-53-24.451269.json,1791481806.948551,1 +v1annealCT_merge3_116k_120k,polymath_es_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8cb638743e_2026-10-08T18-00-34.651547.json,1791482233.4068434,1 +v1annealCT_merge3_116k_120k,polymath_fr_high,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/0d77ae9e98_2026-10-08T17-37-19.389817.json,1791480841.4001672,1 +v1annealCT_merge3_116k_120k,polymath_fr_low,0,lm-eval,vllm,,exact_match,none,0.512,0.044888392062263534,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/46891087c0_2026-10-08T17-48-39.514038.json,1791481518.3453858,1 +v1annealCT_merge3_116k_120k,polymath_fr_medium,0,lm-eval,vllm,,exact_match,none,0.08,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/99b3abf0fc_2026-10-08T18-02-57.277009.json,1791482375.394338,1 +v1annealCT_merge3_116k_120k,polymath_fr_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9dc686db4b_2026-10-08T17-42-01.784429.json,1791481121.520058,1 +v1annealCT_merge3_116k_120k,polymath_it_high,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4f47f39f31_2026-10-08T17-44-14.471555.json,1791481254.6979198,1 +v1annealCT_merge3_116k_120k,polymath_it_low,0,lm-eval,vllm,,exact_match,none,0.392,0.04384135623049351,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/81d1f42ef4_2026-10-08T17-55-43.659054.json,1791481944.7612085,1 +v1annealCT_merge3_116k_120k,polymath_it_medium,0,lm-eval,vllm,,exact_match,none,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/41a209ea1c_2026-10-08T17-48-27.648491.json,1791481519.6157222,1 +v1annealCT_merge3_116k_120k,polymath_it_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/138eb581f7_2026-10-08T17-48-40.071061.json,1791481524.3668628,1 +v1annealCT_merge3_116k_120k,polymath_pt_high,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c5a6afdece_2026-10-08T17-58-06.052561.json,1791482089.047081,1 +v1annealCT_merge3_116k_120k,polymath_pt_low,0,lm-eval,vllm,,exact_match,none,0.392,0.04384135623049351,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3f7cdf6ded_2026-10-08T18-12-09.273994.json,1791482933.8732631,1 +v1annealCT_merge3_116k_120k,polymath_pt_medium,0,lm-eval,vllm,,exact_match,none,0.048,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/12e9cb2a6a_2026-10-08T17-58-15.340000.json,1791482089.0664968,1 +v1annealCT_merge3_116k_120k,polymath_pt_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/ff00863adb_2026-10-08T17-44-15.252498.json,1791481252.7513602,1 +v1annealCT_merge3_116k_120k,sib200_als_Latn,0,lm-eval,vllm,,acc,none,0.3627450980392157,0.0337449935631936,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a060f1700d_2026-10-08T17-55-14.427108.json,1791481943.8569355,1 +v1annealCT_merge3_116k_120k,sib200_bos_Latn,0,lm-eval,vllm,,acc,none,0.4411764705882353,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9fae75006c_2026-10-08T18-14-12.616909.json,1791483079.0753305,1 +v1annealCT_merge3_116k_120k,sib200_bul_Cyrl,0,lm-eval,vllm,,acc,none,0.6029411764705882,0.034341311647191244,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b39d9f3592_2026-10-08T17-43-44.435941.json,1791481252.0446842,1 +v1annealCT_merge3_116k_120k,sib200_cat_Latn,0,lm-eval,vllm,,acc,none,0.5784313725490197,0.03465868196380755,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a4c87c6fe1_2026-10-08T17-36-52.995122.json,1791480847.7362137,1 +v1annealCT_merge3_116k_120k,sib200_ces_Latn,0,lm-eval,vllm,,acc,none,0.5098039215686274,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a857b563db_2026-10-08T17-41-33.182914.json,1791481116.769732,1 +v1annealCT_merge3_116k_120k,sib200_dan_Latn,0,lm-eval,vllm,,acc,none,0.35294117647058826,0.033540924375915215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/1af16c0039_2026-10-08T17-43-48.189258.json,1791481254.5138206,1 +v1annealCT_merge3_116k_120k,sib200_deu_Latn,0,lm-eval,vllm,,acc,none,0.5931372549019608,0.03447891136353379,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f290d97076_2026-10-08T18-11-46.825832.json,1791482931.9840899,1 +v1annealCT_merge3_116k_120k,sib200_ell_Grek,0,lm-eval,vllm,,acc,none,0.4852941176470588,0.035077938347913305,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/d89fe00ac3_2026-10-08T17-36-56.210460.json,1791480842.0044727,1 +v1annealCT_merge3_116k_120k,sib200_eng_Latn,0,lm-eval,vllm,,acc,none,0.45098039215686275,0.034924061041636124,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/dd689c3941_2026-10-08T17-41-30.229293.json,1791481113.0276043,1 +v1annealCT_merge3_116k_120k,sib200_est_Latn,0,lm-eval,vllm,,acc,none,0.4950980392156863,0.03509143375606784,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/07d8a67d4d_2026-10-08T17-43-45.704207.json,1791481252.006315,1 +v1annealCT_merge3_116k_120k,sib200_eus_Latn,0,lm-eval,vllm,,acc,none,0.3284313725490196,0.03296245110172227,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/dd2ba211cd_2026-10-08T17-39-09.410785.json,1791480976.7063305,1 +v1annealCT_merge3_116k_120k,sib200_fin_Latn,0,lm-eval,vllm,,acc,none,0.5588235294117647,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/24a572c3ab_2026-10-08T17-50-41.914375.json,1791481665.9496005,1 +v1annealCT_merge3_116k_120k,sib200_fra_Latn,0,lm-eval,vllm,,acc,none,0.5980392156862745,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2dd95d0fc4_2026-10-08T17-36-53.806983.json,1791480840.8294199,1 +v1annealCT_merge3_116k_120k,sib200_gle_Latn,0,lm-eval,vllm,,acc,none,0.3284313725490196,0.03296245110172227,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3fdd259c45_2026-10-08T17-43-51.854662.json,1791481255.5741653,1 +v1annealCT_merge3_116k_120k,sib200_glg_Latn,0,lm-eval,vllm,,acc,none,0.5343137254901961,0.03501038327635894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6d1b695bd1_2026-10-08T17-41-20.516761.json,1791481110.919881,1 +v1annealCT_merge3_116k_120k,sib200_hrv_Latn,0,lm-eval,vllm,,acc,none,0.4215686274509804,0.03465868196380755,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/8decc19291_2026-10-08T17-34-36.176660.json,1791480695.5480258,1 +v1annealCT_merge3_116k_120k,sib200_hun_Latn,0,lm-eval,vllm,,acc,none,0.4411764705882353,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4ad55c5f57_2026-10-08T17-43-48.397557.json,1791481253.7759767,1 +v1annealCT_merge3_116k_120k,sib200_isl_Latn,0,lm-eval,vllm,,acc,none,0.6029411764705882,0.034341311647191244,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/eb96d5d241_2026-10-08T18-07-17.168385.json,1791482661.2721667,1 +v1annealCT_merge3_116k_120k,sib200_ita_Latn,0,lm-eval,vllm,,acc,none,0.5,0.03509312031717982,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/b10d126f1a_2026-10-08T18-07-19.359341.json,1791482660.420717,1 +v1annealCT_merge3_116k_120k,sib200_kat_Geor,0,lm-eval,vllm,,acc,none,0.6323529411764706,0.0338413204567412,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/7c810abd12_2026-10-08T17-37-08.764782.json,1791480849.1789713,1 +v1annealCT_merge3_116k_120k,sib200_lit_Latn,0,lm-eval,vllm,,acc,none,0.46568627450980393,0.03501038327635894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c5088d223f_2026-10-08T17-55-24.713338.json,1791481950.169109,1 +v1annealCT_merge3_116k_120k,sib200_lvs_Latn,0,lm-eval,vllm,,acc,none,0.39705882352941174,0.034341311647191244,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/a6a53308fc_2026-10-08T18-00-13.348795.json,1791482233.6747189,1 +v1annealCT_merge3_116k_120k,sib200_mkd_Cyrl,0,lm-eval,vllm,,acc,none,0.49019607843137253,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/26ba67771e_2026-10-08T17-48-05.060003.json,1791481525.7041032,1 +v1annealCT_merge3_116k_120k,sib200_mlt_Latn,0,lm-eval,vllm,,acc,none,0.30392156862745096,0.03228210387037892,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/141ae336dc_2026-10-08T17-39-14.189181.json,1791480982.6542423,1 +v1annealCT_merge3_116k_120k,sib200_nld_Latn,0,lm-eval,vllm,,acc,none,0.5980392156862745,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/6509ba4781_2026-10-08T17-41-27.610180.json,1791481115.6634774,1 +v1annealCT_merge3_116k_120k,sib200_nob_Latn,0,lm-eval,vllm,,acc,none,0.3235294117647059,0.032834720561085606,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/aca93267dd_2026-10-08T17-34-33.153237.json,1791480695.6344543,1 +v1annealCT_merge3_116k_120k,sib200_pol_Latn,0,lm-eval,vllm,,acc,none,0.5441176470588235,0.034956245220154746,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/04716dd060_2026-10-08T17-34-29.899220.json,1791480695.8115015,1 +v1annealCT_merge3_116k_120k,sib200_por_Latn,0,lm-eval,vllm,,acc,none,0.5980392156862745,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/9aa1688150_2026-10-08T17-57-43.863075.json,1791482086.4539173,1 +v1annealCT_merge3_116k_120k,sib200_ron_Latn,0,lm-eval,vllm,,acc,none,0.6078431372549019,0.03426712349247272,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/cb29075845_2026-10-08T17-41-29.677720.json,1791481120.4017417,1 +v1annealCT_merge3_116k_120k,sib200_slk_Latn,0,lm-eval,vllm,,acc,none,0.553921568627451,0.034888454513049706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/dd48a600c5_2026-10-08T17-55-24.169452.json,1791481944.3581908,1 +v1annealCT_merge3_116k_120k,sib200_slv_Latn,0,lm-eval,vllm,,acc,none,0.39705882352941174,0.034341311647191244,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/c81ca16be5_2026-10-08T17-32-05.546006.json,1791480549.2380805,1 +v1annealCT_merge3_116k_120k,sib200_spa_Latn,0,lm-eval,vllm,,acc,none,0.5392156862745098,0.03498501649369533,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/158827ac29_2026-10-08T17-48-18.984562.json,1791481519.8529794,1 +v1annealCT_merge3_116k_120k,sib200_srp_Cyrl,0,lm-eval,vllm,,acc,none,0.4950980392156863,0.03509143375606784,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5e9b643e8b_2026-10-08T17-37-07.481246.json,1791480848.6678586,1 +v1annealCT_merge3_116k_120k,sib200_swe_Latn,0,lm-eval,vllm,,acc,none,0.5294117647058824,0.03503235296367989,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/2c49827782_2026-10-08T17-53-04.019323.json,1791481801.127876,1 +v1annealCT_merge3_116k_120k,sib200_tur_Latn,0,lm-eval,vllm,,acc,none,0.49019607843137253,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/634ded8a73_2026-10-08T17-41-24.333221.json,1791481112.4463308,1 +v1annealCT_merge3_116k_120k,sib200_ukr_Cyrl,0,lm-eval,vllm,,acc,none,0.5490196078431373,0.034924061041636124,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/52d4b81045_2026-10-08T17-39-11.662128.json,1791480977.6559703,1 +v1annealCT_merge3_116k_120k,social_iqa,0,lm-eval,vllm,,acc,none,0.5255885363357216,0.011299244540814952,1954,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/f51eb73bdb_2026-10-08T17-37-16.653164.json,1791480850.9329007,1 +v1annealCT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_exact,none,78.0195681511471,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/34574ca8e2_2026-10-08T18-42-55.270258.json,1791483085.873549,1 +v1annealCT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_f1,none,84.31245927318275,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/34574ca8e2_2026-10-08T18-42-55.270258.json,1791483085.873549,1 +v1annealCT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_exact,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/34574ca8e2_2026-10-08T18-42-55.270258.json,1791483085.873549,1 +v1annealCT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_f1,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/34574ca8e2_2026-10-08T18-42-55.270258.json,1791483085.873549,1 +v1annealCT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_exact,none,61.079760801819255,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/34574ca8e2_2026-10-08T18-42-55.270258.json,1791483085.873549,1 +v1annealCT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_f1,none,62.50243130181933,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/34574ca8e2_2026-10-08T18-42-55.270258.json,1791483085.873549,1 +v1annealCT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,exact,none,38.95392908279289,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/34574ca8e2_2026-10-08T18-42-55.270258.json,1791483085.873549,1 +v1annealCT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,f1,none,42.09586949982543,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/34574ca8e2_2026-10-08T18-42-55.270258.json,1791483085.873549,1 +v1annealCT_merge3_116k_120k,winogrande,0,lm-eval,vllm,,acc,none,0.7316495659037096,0.012453340359561227,1267,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/155b824837_2026-10-08T17-55-14.905709.json,1791481944.6544247,1 +v1annealCT_merge3_116k_120k,wsc273,0,lm-eval,vllm,,acc,none,0.8534798534798534,0.021441781058034026,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fec2c3c0b5_2026-10-08T18-00-14.126612.json,1791482234.428244,1 +v1annealCT_merge3_116k_120k,xcopa:et,0,lighteval,hf/accelerate,,acc,none,0.666,0.021113492347743738,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/0982c29554/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-14-46.849731.json,1791483286.932519,1 +v1annealCT_merge3_116k_120k,xcopa:it,0,lighteval,hf/accelerate,,acc,none,0.694,0.020629569998345396,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/4f783b09cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T18-17-02.928996.json,1791483423.01009,1 +v1annealCT_merge3_116k_120k,xcopa:tr,0,lighteval,hf/accelerate,,acc,none,0.656,0.02126575803797874,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/lighteval/2026-10-08-19-25-49/results/d14b5f2a2b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealCT_merge3_116k_120k/results_2026-10-08T17-49-00.964615.json,1791481741.0481179,1 +v1annealCT_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc,none,0.504,0.01581879370351084,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/299d113df8_2026-10-08T18-02-32.574414.json,1791482376.8187351,1 +v1annealCT_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc_norm,none,0.472,0.015794475789511517,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/299d113df8_2026-10-08T18-02-32.574414.json,1791482376.8187351,1 +v1annealCT_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc,none,0.653,0.015060472031706637,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/10dc11b882_2026-10-08T18-09-30.582326.json,1791482797.9408464,1 +v1annealCT_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc_norm,none,0.608,0.015445859463771338,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/10dc11b882_2026-10-08T18-09-30.582326.json,1791482797.9408464,1 +v1annealCT_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc,none,0.485,0.01581217964181488,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5fc10d1d56_2026-10-08T17-34-36.027551.json,1791480701.159804,1 +v1annealCT_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc_norm,none,0.441,0.015708779894242766,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/5fc10d1d56_2026-10-08T17-34-36.027551.json,1791480701.159804,1 +v1annealCT_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc,none,0.497,0.01581901517924682,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fe381890dc_2026-10-08T17-37-08.271942.json,1791480850.2190535,1 +v1annealCT_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc_norm,none,0.442,0.015712507211864152,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/fe381890dc_2026-10-08T17-37-08.271942.json,1791480850.2190535,1 +v1annealCT_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc,none,0.48,0.015806639423035177,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3a458141ba_2026-10-08T18-09-33.900163.json,1791482795.8057446,1 +v1annealCT_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc_norm,none,0.45,0.015740004693383918,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/3a458141ba_2026-10-08T18-09-33.900163.json,1791482795.8057446,1 +v1annealCT_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc,none,0.414,0.015583544104177552,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e06874550_2026-10-08T17-55-22.026542.json,1791481941.096092,1 +v1annealCT_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc_norm,none,0.392,0.015445859463771338,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/4e06874550_2026-10-08T17-55-22.026542.json,1791481941.096092,1 +v1annealCT_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.48,0.015806639423035177,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/275224331b_2026-10-08T18-14-19.654881.json,1791483079.6989682,1 +v1annealCT_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.467,0.015784807891138876,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/275224331b_2026-10-08T18-14-19.654881.json,1791483079.6989682,1 +v1annealCT_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.444,0.01571976816340213,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e5bbfc56cc_2026-10-08T17-39-15.521786.json,1791480980.3980927,1 +v1annealCT_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.414,0.015583544104177552,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/vllm/2026-10-08-19-25-47/results/e5bbfc56cc_2026-10-08T17-39-15.521786.json,1791480980.3980927,1 +v1annealCT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@1,all,0.203125,0.05968423706252458,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fb09b4eae3_2026-10-08T20-37-21.644852.json,1791490693.51873,1 +v1annealCT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@16,all,0.4331097269146755,0.08767774804181316,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fb09b4eae3_2026-10-08T20-37-21.644852.json,1791490693.51873,1 +v1annealCT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@32,all,0.4666666666666667,0.09264111117062016,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fb09b4eae3_2026-10-08T20-37-21.644852.json,1791490693.51873,1 +v1annealCT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@4,all,0.3223934000741565,0.07595085256026059,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fb09b4eae3_2026-10-08T20-37-21.644852.json,1791490693.51873,1 +v1annealCT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,think_closed,all,0.18958333333333333,0.06015599731872095,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fb09b4eae3_2026-10-08T20-37-21.644852.json,1791490693.51873,1 +v1annealCT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@1,all,0.18958333333333333,0.06453117100015573,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fcc7d1639d_2026-10-08T20-37-47.685883.json,1791490692.498954,1 +v1annealCT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@16,all,0.30691095312558775,0.0823499788205768,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fcc7d1639d_2026-10-08T20-37-47.685883.json,1791490692.498954,1 +v1annealCT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@32,all,0.3333333333333333,0.0875376219064817,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fcc7d1639d_2026-10-08T20-37-47.685883.json,1791490692.498954,1 +v1annealCT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@4,all,0.2521459028550241,0.07530665206730405,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fcc7d1639d_2026-10-08T20-37-47.685883.json,1791490692.498954,1 +v1annealCT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,think_closed,all,0.17708333333333334,0.061656181152658994,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fcc7d1639d_2026-10-08T20-37-47.685883.json,1791490692.498954,1 +v1annealCT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@1,all,0.5625,0.06525383437500838,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/7eebe68849_2026-10-08T20-37-51.654636.json,1791490694.6337764,1 +v1annealCT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@16,all,0.8648875703630925,0.04937719752787791,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/7eebe68849_2026-10-08T20-37-51.654636.json,1791490694.6337764,1 +v1annealCT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@32,all,0.9,0.048038446141526144,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/7eebe68849_2026-10-08T20-37-51.654636.json,1791490694.6337764,1 +v1annealCT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@4,all,0.7302871245828698,0.0569643725565103,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/7eebe68849_2026-10-08T20-37-51.654636.json,1791490694.6337764,1 +v1annealCT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,think_closed,all,0.51328125,0.06951684343692753,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/7eebe68849_2026-10-08T20-37-51.654636.json,1791490694.6337764,1 +v1annealCT_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,pass@1,all,0.4393939393939394,0.030283796387856683,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/8486f5b434_2026-10-08T20-42-50.828159.json,1791490692.042662,1 +v1annealCT_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,think_closed,all,0.39141414141414144,0.029703712181588727,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/8486f5b434_2026-10-08T20-42-50.828159.json,1791490692.042662,1 +v1annealCT_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@1,all,0.5884146341463414,0.031186352394477444,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/0448f75bb0_2026-10-08T20-23-02.545811.json,1791490686.7450988,1 +v1annealCT_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@16,all,0.7898526837467189,0.03165145841245793,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/0448f75bb0_2026-10-08T20-23-02.545811.json,1791490686.7450988,1 +v1annealCT_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@1,all,0.35449029126213594,0.018760087631947663,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/8ad373e4d9_2026-10-08T20-50-57.331695.json,1791490694.1051693,1 +v1annealCT_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@4,all,0.4388349514563107,0.021888416923159137,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/8ad373e4d9_2026-10-08T20-50-57.331695.json,1791490694.1051693,1 +v1annealCT_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,think_closed,all,0.4330097087378641,0.019957913005424134,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/8ad373e4d9_2026-10-08T20-50-57.331695.json,1791490694.1051693,1 +v1annealCT_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@1,all,0.21404109589041095,0.017078237811148665,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/93e998b502_2026-10-08T21-23-44.884481.json,1791492285.2284896,1 +v1annealCT_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@4,all,0.2543751747274252,0.018928538098298354,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/93e998b502_2026-10-08T21-23-44.884481.json,1791492285.2284896,1 +v1annealCT_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@1,all,0.747,0.01793391341846508,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/1a80835137_2026-10-08T20-39-04.781566.json,1791490692.442779,1 +v1annealCT_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@4,all,0.804,0.017770751227744897,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/1a80835137_2026-10-08T20-39-04.781566.json,1791490692.442779,1 +v1annealCT_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,think_closed,all,0.78,0.017140232645746108,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/1a80835137_2026-10-08T20-39-04.781566.json,1791490692.442779,1 +v1annealCT_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@1,all,0.638625,0.01913525305735825,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/88ebc3fa62_2026-10-08T20-25-09.762684.json,1791490693.1470287,1 +v1annealCT_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@16,all,0.7655694760229992,0.018550019664867183,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/88ebc3fa62_2026-10-08T20-25-09.762684.json,1791490693.1470287,1 +v1annealCT_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@1,all,0.094,0.022300007232748716,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/cab9d18773_2026-10-08T20-30-26.628138.json,1791490699.0605721,1 +v1annealCT_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@4,all,0.144,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/cab9d18773_2026-10-08T20-30-26.628138.json,1791490699.0605721,1 +v1annealCT_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,think_closed,all,0.11,0.023314124197506846,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/cab9d18773_2026-10-08T20-30-26.628138.json,1791490699.0605721,1 +v1annealCT_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@1,all,0.616,0.03899379603260316,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/6fe06e1cdd_2026-10-08T20-23-24.936831.json,1791490694.5233364,1 +v1annealCT_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@4,all,0.76,0.03835319728439186,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/6fe06e1cdd_2026-10-08T20-23-24.936831.json,1791490694.5233364,1 +v1annealCT_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,think_closed,all,0.984,0.010137760775851198,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/6fe06e1cdd_2026-10-08T20-23-24.936831.json,1791490694.5233364,1 +v1annealCT_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@1,all,0.232,0.03445146188199351,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/48a353fe03_2026-10-08T20-30-16.402267.json,1791490692.0332136,1 +v1annealCT_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@4,all,0.304,0.041307657651398745,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/48a353fe03_2026-10-08T20-30-16.402267.json,1791490692.0332136,1 +v1annealCT_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,think_closed,all,0.286,0.03611183346396347,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/48a353fe03_2026-10-08T20-30-16.402267.json,1791490692.0332136,1 +v1annealCT_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/ed595c8fe3_2026-10-08T20-30-14.061046.json,1791490692.3349822,1 +v1annealCT_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/ed595c8fe3_2026-10-08T20-30-14.061046.json,1791490692.3349822,1 +v1annealCT_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,think_closed,all,0.014,0.006540198280510086,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/ed595c8fe3_2026-10-08T20-30-14.061046.json,1791490692.3349822,1 +v1annealCT_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@1,all,0.082,0.022320249738457157,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/30b5b0e211_2026-10-08T20-30-21.963544.json,1791490693.5040648,1 +v1annealCT_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@4,all,0.12,0.029182407426835203,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/30b5b0e211_2026-10-08T20-30-21.963544.json,1791490693.5040648,1 +v1annealCT_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,think_closed,all,0.102,0.02411263890242438,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/30b5b0e211_2026-10-08T20-30-21.963544.json,1791490693.5040648,1 +v1annealCT_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@1,all,0.868,0.027323627964845557,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b9999059b3_2026-10-08T20-22-57.855095.json,1791490691.9604528,1 +v1annealCT_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@4,all,0.912,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b9999059b3_2026-10-08T20-22-57.855095.json,1791490691.9604528,1 +v1annealCT_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,think_closed,all,0.988,0.008915372732967587,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b9999059b3_2026-10-08T20-22-57.855095.json,1791490691.9604528,1 +v1annealCT_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@1,all,0.25,0.03489615932282335,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/9858d04076_2026-10-08T20-30-20.847346.json,1791490693.8380654,1 +v1annealCT_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@4,all,0.336,0.04241728193144408,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/9858d04076_2026-10-08T20-30-20.847346.json,1791490693.8380654,1 +v1annealCT_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,think_closed,all,0.298,0.03633357995378468,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/9858d04076_2026-10-08T20-30-20.847346.json,1791490693.8380654,1 +v1annealCT_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@1,all,0.002,0.002,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b185e0ecb0_2026-10-08T20-33-18.363908.json,1791490853.413425,1 +v1annealCT_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b185e0ecb0_2026-10-08T20-33-18.363908.json,1791490853.413425,1 +v1annealCT_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,think_closed,all,0.018,0.007607297006291753,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b185e0ecb0_2026-10-08T20-33-18.363908.json,1791490853.413425,1 +v1annealCT_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@1,all,0.072,0.021025330345300932,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/0793c91aaf_2026-10-08T20-30-12.330260.json,1791490694.006458,1 +v1annealCT_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@4,all,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/0793c91aaf_2026-10-08T20-30-12.330260.json,1791490694.006458,1 +v1annealCT_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,think_closed,all,0.088,0.02276386497032296,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/0793c91aaf_2026-10-08T20-30-12.330260.json,1791490694.006458,1 +v1annealCT_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@1,all,0.872,0.02703283547000549,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/45f7910af0_2026-10-08T20-24-01.787247.json,1791490695.7866018,1 +v1annealCT_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@4,all,0.936,0.021979462554702022,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/45f7910af0_2026-10-08T20-24-01.787247.json,1791490695.7866018,1 +v1annealCT_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,think_closed,all,0.96,0.015397947077242095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/45f7910af0_2026-10-08T20-24-01.787247.json,1791490695.7866018,1 +v1annealCT_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@1,all,0.226,0.031163460820688393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/be419dca21_2026-10-08T20-30-28.352396.json,1791490695.1684434,1 +v1annealCT_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@4,all,0.36,0.043105272486425976,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/be419dca21_2026-10-08T20-30-28.352396.json,1791490695.1684434,1 +v1annealCT_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,think_closed,all,0.286,0.034042667724584266,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/be419dca21_2026-10-08T20-30-28.352396.json,1791490695.1684434,1 +v1annealCT_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/e3343ca239_2026-10-08T20-30-27.167171.json,1791490693.5355604,1 +v1annealCT_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/e3343ca239_2026-10-08T20-30-27.167171.json,1791490693.5355604,1 +v1annealCT_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,think_closed,all,0.016,0.007902633289178096,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/e3343ca239_2026-10-08T20-30-27.167171.json,1791490693.5355604,1 +v1annealCT_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@1,all,0.094,0.02156460660583717,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/faf39a589a_2026-10-08T20-30-32.423569.json,1791490695.6295457,1 +v1annealCT_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@4,all,0.168,0.03357418363045649,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/faf39a589a_2026-10-08T20-30-32.423569.json,1791490695.6295457,1 +v1annealCT_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,think_closed,all,0.112,0.02279926427788632,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/faf39a589a_2026-10-08T20-30-32.423569.json,1791490695.6295457,1 +v1annealCT_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@1,all,0.828,0.028598443449634376,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/485dc68b39_2026-10-08T20-23-38.400715.json,1791490694.4983995,1 +v1annealCT_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@4,all,0.904,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/485dc68b39_2026-10-08T20-23-38.400715.json,1791490694.4983995,1 +v1annealCT_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,think_closed,all,0.974,0.008900887958603505,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/485dc68b39_2026-10-08T20-23-38.400715.json,1791490694.4983995,1 +v1annealCT_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@1,all,0.22,0.034849908594317115,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/4e1fecd2d7_2026-10-08T20-30-12.630644.json,1791490693.169025,1 +v1annealCT_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@4,all,0.28,0.04032129030193482,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/4e1fecd2d7_2026-10-08T20-30-12.630644.json,1791490693.169025,1 +v1annealCT_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,think_closed,all,0.282,0.03777864219968225,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/4e1fecd2d7_2026-10-08T20-30-12.630644.json,1791490693.169025,1 +v1annealCT_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@1,all,0.006,0.004457686366483794,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/1291a13630_2026-10-08T20-30-31.405350.json,1791490694.753796,1 +v1annealCT_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/1291a13630_2026-10-08T20-30-31.405350.json,1791490694.753796,1 +v1annealCT_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,think_closed,all,0.022,0.008526996975451253,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/1291a13630_2026-10-08T20-30-31.405350.json,1791490694.753796,1 +v1annealCT_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@1,all,0.094,0.024040288764300807,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b489b64182_2026-10-08T20-30-11.758172.json,1791490686.5095148,1 +v1annealCT_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@4,all,0.12,0.029182407426835203,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b489b64182_2026-10-08T20-30-11.758172.json,1791490686.5095148,1 +v1annealCT_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,think_closed,all,0.108,0.025611237452941776,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b489b64182_2026-10-08T20-30-11.758172.json,1791490686.5095148,1 +v1annealCT_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@1,all,0.78,0.02452779858091236,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/af8339cbf2_2026-10-08T20-23-16.430378.json,1791490697.141525,1 +v1annealCT_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@4,all,0.96,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/af8339cbf2_2026-10-08T20-23-16.430378.json,1791490697.141525,1 +v1annealCT_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,think_closed,all,0.978,0.006360158245140274,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/af8339cbf2_2026-10-08T20-23-16.430378.json,1791490697.141525,1 +v1annealCT_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@1,all,0.224,0.03544919126426332,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/44d8e3a9bd_2026-10-08T20-30-15.292168.json,1791490694.7176445,1 +v1annealCT_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@4,all,0.28,0.04032129030193482,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/44d8e3a9bd_2026-10-08T20-30-15.292168.json,1791490694.7176445,1 +v1annealCT_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,think_closed,all,0.286,0.03827995348364046,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/44d8e3a9bd_2026-10-08T20-30-15.292168.json,1791490694.7176445,1 +v1annealCT_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@1,all,0.014,0.008662116257850393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/f1eac1b7d7_2026-10-08T20-30-34.983408.json,1791490692.0154977,1 +v1annealCT_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@4,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/f1eac1b7d7_2026-10-08T20-30-34.983408.json,1791490692.0154977,1 +v1annealCT_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,think_closed,all,0.034,0.013423619049537155,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/f1eac1b7d7_2026-10-08T20-30-34.983408.json,1791490692.0154977,1 +v1annealCT_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@1,all,0.074,0.021631816471830743,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/8211fcd482_2026-10-08T20-30-19.784190.json,1791490692.0185764,1 +v1annealCT_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@4,all,0.104,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/8211fcd482_2026-10-08T20-30-19.784190.json,1791490692.0185764,1 +v1annealCT_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,think_closed,all,0.092,0.023509778336244576,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/8211fcd482_2026-10-08T20-30-19.784190.json,1791490692.0185764,1 +v1annealCT_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@1,all,0.82,0.028341238618867965,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b8b2234032_2026-10-08T20-25-33.673300.json,1791490849.4707026,1 +v1annealCT_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@4,all,0.928,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b8b2234032_2026-10-08T20-25-33.673300.json,1791490849.4707026,1 +v1annealCT_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,think_closed,all,0.99,0.008230548917531015,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/b8b2234032_2026-10-08T20-25-33.673300.json,1791490849.4707026,1 +v1annealCT_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@1,all,0.208,0.03644881519380648,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/ae5b8410e0_2026-10-08T20-29-42.548689.json,1791490684.450527,1 +v1annealCT_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@4,all,0.208,0.03644881519380648,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/ae5b8410e0_2026-10-08T20-29-42.548689.json,1791490684.450527,1 +v1annealCT_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,think_closed,all,0.304,0.041307657651398745,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/ae5b8410e0_2026-10-08T20-29-42.548689.json,1791490684.450527,1 +v1annealCT_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@1,all,0.006,0.006,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fcb87fe3f7_2026-10-08T20-30-11.770836.json,1791490693.9706562,1 +v1annealCT_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fcb87fe3f7_2026-10-08T20-30-11.770836.json,1791490693.9706562,1 +v1annealCT_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,think_closed,all,0.03,0.013198240351921794,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealCT_merge3_116k_120k/cot/2026-10-08-22-14-55/results/fcb87fe3f7_2026-10-08T20-30-11.770836.json,1791490693.9706562,1 diff --git a/results/v1annealC_120k_l0fixed.flag-evals-438.tasks.csv b/results/v1annealC_120k_l0fix.flag-evals-471.tasks.csv similarity index 95% rename from results/v1annealC_120k_l0fixed.flag-evals-438.tasks.csv rename to results/v1annealC_120k_l0fix.flag-evals-471.tasks.csv index a36b66b..63634f4 100644 --- a/results/v1annealC_120k_l0fixed.flag-evals-438.tasks.csv +++ b/results/v1annealC_120k_l0fix.flag-evals-471.tasks.csv @@ -2021,3 +2021,104 @@ v1annealC_120k_l0fix,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.478,0.01580397942 v1annealC_120k_l0fix,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.445,0.015723301886761007,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/vllm/2026-10-03-18-08-17/results/c2c27396a2_2026-10-03T16-46-30.810501.json,1791045819.8572567,1 v1annealC_120k_l0fix,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.462,0.015773547629015002,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/vllm/2026-10-03-18-08-17/results/4412e01357_2026-10-03T16-24-53.423819.json,1791044515.1311574,1 v1annealC_120k_l0fix,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.398,0.015486634102859016,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/vllm/2026-10-03-18-08-17/results/4412e01357_2026-10-03T16-24-53.423819.json,1791044515.1311574,1 +v1annealC_120k_l0fix,aime24_cot,0,lm-eval,vllm,,pass@1,all,0.19791666666666666,0.05895730523858913,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0385b59402_2026-10-08T22-27-47.706889.json,1791497334.8675747,1 +v1annealC_120k_l0fix,aime24_cot,0,lm-eval,vllm,,pass@16,all,0.455060848183718,0.08745024581781391,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0385b59402_2026-10-08T22-27-47.706889.json,1791497334.8675747,1 +v1annealC_120k_l0fix,aime24_cot,0,lm-eval,vllm,,pass@32,all,0.5,0.09284766908852593,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0385b59402_2026-10-08T22-27-47.706889.json,1791497334.8675747,1 +v1annealC_120k_l0fix,aime24_cot,0,lm-eval,vllm,,pass@4,all,0.3282109751575825,0.07355657160615263,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0385b59402_2026-10-08T22-27-47.706889.json,1791497334.8675747,1 +v1annealC_120k_l0fix,aime24_cot,0,lm-eval,vllm,,think_closed,all,0.17083333333333334,0.056056766862807125,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0385b59402_2026-10-08T22-27-47.706889.json,1791497334.8675747,1 +v1annealC_120k_l0fix,aime25_cot,0,lm-eval,vllm,,pass@1,all,0.20416666666666666,0.06587056091319671,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/e5bf6b8c89_2026-10-08T22-28-30.159554.json,1791497344.0952592,1 +v1annealC_120k_l0fix,aime25_cot,0,lm-eval,vllm,,pass@16,all,0.3344086021505376,0.08334714682120471,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/e5bf6b8c89_2026-10-08T22-28-30.159554.json,1791497344.0952592,1 +v1annealC_120k_l0fix,aime25_cot,0,lm-eval,vllm,,pass@32,all,0.36666666666666664,0.08948554539839963,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/e5bf6b8c89_2026-10-08T22-28-30.159554.json,1791497344.0952592,1 +v1annealC_120k_l0fix,aime25_cot,0,lm-eval,vllm,,pass@4,all,0.26728494623655913,0.076661877062548,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/e5bf6b8c89_2026-10-08T22-28-30.159554.json,1791497344.0952592,1 +v1annealC_120k_l0fix,aime25_cot,0,lm-eval,vllm,,think_closed,all,0.203125,0.0618999572331013,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/e5bf6b8c89_2026-10-08T22-28-30.159554.json,1791497344.0952592,1 +v1annealC_120k_l0fix,amc23_cot,0,lm-eval,vllm,,pass@1,all,0.5734375,0.06074818554718849,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c7c1401ca8_2026-10-08T22-27-47.272801.json,1791497340.6755402,1 +v1annealC_120k_l0fix,amc23_cot,0,lm-eval,vllm,,pass@16,all,0.9075444203062423,0.04225587172904582,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c7c1401ca8_2026-10-08T22-27-47.272801.json,1791497340.6755402,1 +v1annealC_120k_l0fix,amc23_cot,0,lm-eval,vllm,,pass@32,all,0.925,0.04217636961434867,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c7c1401ca8_2026-10-08T22-27-47.272801.json,1791497340.6755402,1 +v1annealC_120k_l0fix,amc23_cot,0,lm-eval,vllm,,pass@4,all,0.7750083426028921,0.050627552837027946,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c7c1401ca8_2026-10-08T22-27-47.272801.json,1791497340.6755402,1 +v1annealC_120k_l0fix,amc23_cot,0,lm-eval,vllm,,think_closed,all,0.5328125,0.06728432945035072,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c7c1401ca8_2026-10-08T22-27-47.272801.json,1791497340.6755402,1 +v1annealC_120k_l0fix,gpqa_diamond_cot,0,lm-eval,vllm,,pass@1,all,0.44191919191919193,0.0296136701326619,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/de344a4459_2026-10-08T22-34-46.364471.json,1791497338.126639,1 +v1annealC_120k_l0fix,gpqa_diamond_cot,0,lm-eval,vllm,,think_closed,all,0.32765151515151514,0.028421906559188612,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/de344a4459_2026-10-08T22-34-46.364471.json,1791497338.126639,1 +v1annealC_120k_l0fix,humaneval_cont,0,lm-eval,vllm,,pass@1,all,0.640625,0.03047527927552581,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0c2919ccf0_2026-10-08T22-13-50.822534.json,1791497333.9572299,1 +v1annealC_120k_l0fix,humaneval_cont,0,lm-eval,vllm,,pass@16,all,0.840362290148342,0.027379702805282295,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0c2919ccf0_2026-10-08T22-13-50.822534.json,1791497333.9572299,1 +v1annealC_120k_l0fix,jeebench_cot,0,lm-eval,vllm,,pass@1,all,0.3503640776699029,0.01886654345955106,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c81e96a9f3_2026-10-08T22-42-40.497501.json,1791497342.494903,1 +v1annealC_120k_l0fix,jeebench_cot,0,lm-eval,vllm,,pass@4,all,0.4524271844660194,0.0219540033496889,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c81e96a9f3_2026-10-08T22-42-40.497501.json,1791497342.494903,1 +v1annealC_120k_l0fix,jeebench_cot,0,lm-eval,vllm,,think_closed,all,0.3975728155339806,0.019354498188437798,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c81e96a9f3_2026-10-08T22-42-40.497501.json,1791497342.494903,1 +v1annealC_120k_l0fix,livecodebench_cont,0,lm-eval,vllm,,pass@1,all,0.18272994129158512,0.015542233345025025,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/7d2ceaf17a_2026-10-08T22-18-34.243416.json,1791497341.036885,1 +v1annealC_120k_l0fix,livecodebench_cont,0,lm-eval,vllm,,pass@4,all,0.23760134190662566,0.018369703394233345,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/7d2ceaf17a_2026-10-08T22-18-34.243416.json,1791497341.036885,1 +v1annealC_120k_l0fix,math500_cot,0,lm-eval,vllm,,pass@1,all,0.7355,0.018302991531386228,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/59500c2589_2026-10-08T22-30-38.825660.json,1791497339.7906113,1 +v1annealC_120k_l0fix,math500_cot,0,lm-eval,vllm,,pass@4,all,0.81,0.01756180041075899,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/59500c2589_2026-10-08T22-30-38.825660.json,1791497339.7906113,1 +v1annealC_120k_l0fix,math500_cot,0,lm-eval,vllm,,think_closed,all,0.775,0.017272715287029238,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/59500c2589_2026-10-08T22-30-38.825660.json,1791497339.7906113,1 +v1annealC_120k_l0fix,mbpp_cont,3,lm-eval,vllm,,pass@1,all,0.6294375,0.019539462752255845,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/4f588302ab_2026-10-08T22-15-48.695548.json,1791497338.8421266,1 +v1annealC_120k_l0fix,mbpp_cont,3,lm-eval,vllm,,pass@16,all,0.7402422659005727,0.019544566887066364,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/4f588302ab_2026-10-08T22-15-48.695548.json,1791497338.8421266,1 +v1annealC_120k_l0fix,polymath_de_high_cot,0,lm-eval,vllm,,pass@1,all,0.076,0.021669065210497065,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2c2f9bc32c_2026-10-08T22-20-53.422289.json,1791497334.840362,1 +v1annealC_120k_l0fix,polymath_de_high_cot,0,lm-eval,vllm,,pass@4,all,0.112,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2c2f9bc32c_2026-10-08T22-20-53.422289.json,1791497334.840362,1 +v1annealC_120k_l0fix,polymath_de_high_cot,0,lm-eval,vllm,,think_closed,all,0.08,0.02173892005508301,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2c2f9bc32c_2026-10-08T22-20-53.422289.json,1791497334.840362,1 +v1annealC_120k_l0fix,polymath_de_low_cot,0,lm-eval,vllm,,pass@1,all,0.746,0.03431166452652283,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/16a2fffd8b_2026-10-08T22-14-53.680302.json,1791497341.2883744,1 +v1annealC_120k_l0fix,polymath_de_low_cot,0,lm-eval,vllm,,pass@4,all,0.872,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/16a2fffd8b_2026-10-08T22-14-53.680302.json,1791497341.2883744,1 +v1annealC_120k_l0fix,polymath_de_low_cot,0,lm-eval,vllm,,think_closed,all,0.958,0.01697626426476381,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/16a2fffd8b_2026-10-08T22-14-53.680302.json,1791497341.2883744,1 +v1annealC_120k_l0fix,polymath_de_medium_cot,0,lm-eval,vllm,,pass@1,all,0.248,0.03425426745253323,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/48f8ee0bf8_2026-10-08T22-20-50.015740.json,1791497340.5637195,1 +v1annealC_120k_l0fix,polymath_de_medium_cot,0,lm-eval,vllm,,pass@4,all,0.344,0.04265994570720801,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/48f8ee0bf8_2026-10-08T22-20-50.015740.json,1791497340.5637195,1 +v1annealC_120k_l0fix,polymath_de_medium_cot,0,lm-eval,vllm,,think_closed,all,0.294,0.03581583718899206,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/48f8ee0bf8_2026-10-08T22-20-50.015740.json,1791497340.5637195,1 +v1annealC_120k_l0fix,polymath_de_top_cot,0,lm-eval,vllm,,pass@1,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b6ad945d47_2026-10-08T22-21-05.009675.json,1791497339.7219145,1 +v1annealC_120k_l0fix,polymath_de_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b6ad945d47_2026-10-08T22-21-05.009675.json,1791497339.7219145,1 +v1annealC_120k_l0fix,polymath_de_top_cot,0,lm-eval,vllm,,think_closed,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b6ad945d47_2026-10-08T22-21-05.009675.json,1791497339.7219145,1 +v1annealC_120k_l0fix,polymath_en_high_cot,0,lm-eval,vllm,,pass@1,all,0.1,0.02409657986707497,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/83c6e204ed_2026-10-08T22-21-03.418656.json,1791497335.3496542,1 +v1annealC_120k_l0fix,polymath_en_high_cot,0,lm-eval,vllm,,pass@4,all,0.136,0.030783321835464835,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/83c6e204ed_2026-10-08T22-21-03.418656.json,1791497335.3496542,1 +v1annealC_120k_l0fix,polymath_en_high_cot,0,lm-eval,vllm,,think_closed,all,0.13,0.02485441480871901,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/83c6e204ed_2026-10-08T22-21-03.418656.json,1791497335.3496542,1 +v1annealC_120k_l0fix,polymath_en_low_cot,0,lm-eval,vllm,,pass@1,all,0.86,0.02608917709109129,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0530dd5e28_2026-10-08T22-14-47.501495.json,1791497341.1262102,1 +v1annealC_120k_l0fix,polymath_en_low_cot,0,lm-eval,vllm,,pass@4,all,0.952,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0530dd5e28_2026-10-08T22-14-47.501495.json,1791497341.1262102,1 +v1annealC_120k_l0fix,polymath_en_low_cot,0,lm-eval,vllm,,think_closed,all,0.958,0.015485685377564121,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0530dd5e28_2026-10-08T22-14-47.501495.json,1791497341.1262102,1 +v1annealC_120k_l0fix,polymath_en_medium_cot,0,lm-eval,vllm,,pass@1,all,0.248,0.036200160398860474,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/a64bf03f24_2026-10-08T22-20-49.716353.json,1791497344.171263,1 +v1annealC_120k_l0fix,polymath_en_medium_cot,0,lm-eval,vllm,,pass@4,all,0.296,0.04099409870984186,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/a64bf03f24_2026-10-08T22-20-49.716353.json,1791497344.171263,1 +v1annealC_120k_l0fix,polymath_en_medium_cot,0,lm-eval,vllm,,think_closed,all,0.296,0.037715402860147546,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/a64bf03f24_2026-10-08T22-20-49.716353.json,1791497344.171263,1 +v1annealC_120k_l0fix,polymath_en_top_cot,0,lm-eval,vllm,,pass@1,all,0.002,0.002,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/bcf7c15f43_2026-10-08T22-23-36.485078.json,1791497491.759879,1 +v1annealC_120k_l0fix,polymath_en_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/bcf7c15f43_2026-10-08T22-23-36.485078.json,1791497491.759879,1 +v1annealC_120k_l0fix,polymath_en_top_cot,0,lm-eval,vllm,,think_closed,all,0.014,0.006540198280510086,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/bcf7c15f43_2026-10-08T22-23-36.485078.json,1791497491.759879,1 +v1annealC_120k_l0fix,polymath_es_high_cot,0,lm-eval,vllm,,pass@1,all,0.1,0.023417666339201983,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c36ba2c135_2026-10-08T22-21-00.514142.json,1791497336.841793,1 +v1annealC_120k_l0fix,polymath_es_high_cot,0,lm-eval,vllm,,pass@4,all,0.144,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c36ba2c135_2026-10-08T22-21-00.514142.json,1791497336.841793,1 +v1annealC_120k_l0fix,polymath_es_high_cot,0,lm-eval,vllm,,think_closed,all,0.124,0.024531743754020077,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c36ba2c135_2026-10-08T22-21-00.514142.json,1791497336.841793,1 +v1annealC_120k_l0fix,polymath_es_low_cot,0,lm-eval,vllm,,pass@1,all,0.82,0.026273990573286755,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/098fbab6e2_2026-10-08T22-15-11.872324.json,1791497341.261225,1 +v1annealC_120k_l0fix,polymath_es_low_cot,0,lm-eval,vllm,,pass@4,all,0.936,0.021979462554702022,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/098fbab6e2_2026-10-08T22-15-11.872324.json,1791497341.261225,1 +v1annealC_120k_l0fix,polymath_es_low_cot,0,lm-eval,vllm,,think_closed,all,0.938,0.017193397082188453,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/098fbab6e2_2026-10-08T22-15-11.872324.json,1791497341.261225,1 +v1annealC_120k_l0fix,polymath_es_medium_cot,0,lm-eval,vllm,,pass@1,all,0.272,0.03625803581677202,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c3ef6d2e7b_2026-10-08T22-20-33.748641.json,1791497332.6917942,1 +v1annealC_120k_l0fix,polymath_es_medium_cot,0,lm-eval,vllm,,pass@4,all,0.344,0.04265994570720801,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c3ef6d2e7b_2026-10-08T22-20-33.748641.json,1791497332.6917942,1 +v1annealC_120k_l0fix,polymath_es_medium_cot,0,lm-eval,vllm,,think_closed,all,0.33,0.03763148990218251,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c3ef6d2e7b_2026-10-08T22-20-33.748641.json,1791497332.6917942,1 +v1annealC_120k_l0fix,polymath_es_top_cot,0,lm-eval,vllm,,pass@1,all,0.01,0.005956833971812705,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/68127f0ed0_2026-10-08T22-21-04.549328.json,1791497342.4994714,1 +v1annealC_120k_l0fix,polymath_es_top_cot,0,lm-eval,vllm,,pass@4,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/68127f0ed0_2026-10-08T22-21-04.549328.json,1791497342.4994714,1 +v1annealC_120k_l0fix,polymath_es_top_cot,0,lm-eval,vllm,,think_closed,all,0.032,0.010989731277351011,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/68127f0ed0_2026-10-08T22-21-04.549328.json,1791497342.4994714,1 +v1annealC_120k_l0fix,polymath_fr_high_cot,0,lm-eval,vllm,,pass@1,all,0.08,0.021364728243140042,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/42c10e1b22_2026-10-08T22-20-59.662408.json,1791497339.8490703,1 +v1annealC_120k_l0fix,polymath_fr_high_cot,0,lm-eval,vllm,,pass@4,all,0.128,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/42c10e1b22_2026-10-08T22-20-59.662408.json,1791497339.8490703,1 +v1annealC_120k_l0fix,polymath_fr_high_cot,0,lm-eval,vllm,,think_closed,all,0.108,0.0239852104969009,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/42c10e1b22_2026-10-08T22-20-59.662408.json,1791497339.8490703,1 +v1annealC_120k_l0fix,polymath_fr_low_cot,0,lm-eval,vllm,,pass@1,all,0.828,0.02773957229244427,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/315d262f9d_2026-10-08T22-14-57.507754.json,1791497334.4375737,1 +v1annealC_120k_l0fix,polymath_fr_low_cot,0,lm-eval,vllm,,pass@4,all,0.92,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/315d262f9d_2026-10-08T22-14-57.507754.json,1791497334.4375737,1 +v1annealC_120k_l0fix,polymath_fr_low_cot,0,lm-eval,vllm,,think_closed,all,0.942,0.014793198088223497,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/315d262f9d_2026-10-08T22-14-57.507754.json,1791497334.4375737,1 +v1annealC_120k_l0fix,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@1,all,0.24,0.03279948858767318,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c026441bb4_2026-10-08T22-20-47.417413.json,1791497336.7819383,1 +v1annealC_120k_l0fix,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@4,all,0.36,0.043105272486425976,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c026441bb4_2026-10-08T22-20-47.417413.json,1791497336.7819383,1 +v1annealC_120k_l0fix,polymath_fr_medium_cot,0,lm-eval,vllm,,think_closed,all,0.318,0.035738296076500524,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/c026441bb4_2026-10-08T22-20-47.417413.json,1791497336.7819383,1 +v1annealC_120k_l0fix,polymath_fr_top_cot,0,lm-eval,vllm,,pass@1,all,0.006,0.006,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/47c61dba70_2026-10-08T22-21-13.394781.json,1791497346.3236127,1 +v1annealC_120k_l0fix,polymath_fr_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/47c61dba70_2026-10-08T22-21-13.394781.json,1791497346.3236127,1 +v1annealC_120k_l0fix,polymath_fr_top_cot,0,lm-eval,vllm,,think_closed,all,0.02,0.009245748805139686,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/47c61dba70_2026-10-08T22-21-13.394781.json,1791497346.3236127,1 +v1annealC_120k_l0fix,polymath_it_high_cot,0,lm-eval,vllm,,pass@1,all,0.094,0.022300007232748716,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/e04b106ddd_2026-10-08T22-21-07.160288.json,1791497336.8038688,1 +v1annealC_120k_l0fix,polymath_it_high_cot,0,lm-eval,vllm,,pass@4,all,0.152,0.032241027759172654,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/e04b106ddd_2026-10-08T22-21-07.160288.json,1791497336.8038688,1 +v1annealC_120k_l0fix,polymath_it_high_cot,0,lm-eval,vllm,,think_closed,all,0.128,0.024365496493091183,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/e04b106ddd_2026-10-08T22-21-07.160288.json,1791497336.8038688,1 +v1annealC_120k_l0fix,polymath_it_low_cot,0,lm-eval,vllm,,pass@1,all,0.87,0.022288431832418965,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0ae0ad37e3_2026-10-08T22-14-34.208074.json,1791497341.121447,1 +v1annealC_120k_l0fix,polymath_it_low_cot,0,lm-eval,vllm,,pass@4,all,0.976,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0ae0ad37e3_2026-10-08T22-14-34.208074.json,1791497341.121447,1 +v1annealC_120k_l0fix,polymath_it_low_cot,0,lm-eval,vllm,,think_closed,all,0.974,0.010933818504839661,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/0ae0ad37e3_2026-10-08T22-14-34.208074.json,1791497341.121447,1 +v1annealC_120k_l0fix,polymath_it_medium_cot,0,lm-eval,vllm,,pass@1,all,0.248,0.03529781131842267,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b0e67b96c2_2026-10-08T22-20-43.381630.json,1791497334.286379,1 +v1annealC_120k_l0fix,polymath_it_medium_cot,0,lm-eval,vllm,,pass@4,all,0.32,0.04189079504709142,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b0e67b96c2_2026-10-08T22-20-43.381630.json,1791497334.286379,1 +v1annealC_120k_l0fix,polymath_it_medium_cot,0,lm-eval,vllm,,think_closed,all,0.306,0.037011767962932214,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b0e67b96c2_2026-10-08T22-20-43.381630.json,1791497334.286379,1 +v1annealC_120k_l0fix,polymath_it_top_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.00563399817925698,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/a2d6fd57e6_2026-10-08T22-21-09.452915.json,1791497343.6554816,1 +v1annealC_120k_l0fix,polymath_it_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/a2d6fd57e6_2026-10-08T22-21-09.452915.json,1791497343.6554816,1 +v1annealC_120k_l0fix,polymath_it_top_cot,0,lm-eval,vllm,,think_closed,all,0.036,0.012921599821054817,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/a2d6fd57e6_2026-10-08T22-21-09.452915.json,1791497343.6554816,1 +v1annealC_120k_l0fix,polymath_pt_high_cot,0,lm-eval,vllm,,pass@1,all,0.098,0.023052534672757995,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2b05202af4_2026-10-08T22-20-59.800955.json,1791497334.0130916,1 +v1annealC_120k_l0fix,polymath_pt_high_cot,0,lm-eval,vllm,,pass@4,all,0.152,0.032241027759172654,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2b05202af4_2026-10-08T22-20-59.800955.json,1791497334.0130916,1 +v1annealC_120k_l0fix,polymath_pt_high_cot,0,lm-eval,vllm,,think_closed,all,0.12,0.02452779858091236,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2b05202af4_2026-10-08T22-20-59.800955.json,1791497334.0130916,1 +v1annealC_120k_l0fix,polymath_pt_low_cot,0,lm-eval,vllm,,pass@1,all,0.802,0.024805046312809925,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b7d99ae69f_2026-10-08T22-17-19.443079.json,1791497489.898186,1 +v1annealC_120k_l0fix,polymath_pt_low_cot,0,lm-eval,vllm,,pass@4,all,0.952,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b7d99ae69f_2026-10-08T22-17-19.443079.json,1791497489.898186,1 +v1annealC_120k_l0fix,polymath_pt_low_cot,0,lm-eval,vllm,,think_closed,all,0.96,0.012508061916349223,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/b7d99ae69f_2026-10-08T22-17-19.443079.json,1791497489.898186,1 +v1annealC_120k_l0fix,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@1,all,0.232,0.03338147061837093,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2da574a58b_2026-10-08T22-21-05.902343.json,1791497341.0649164,1 +v1annealC_120k_l0fix,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@4,all,0.344,0.04265994570720801,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2da574a58b_2026-10-08T22-21-05.902343.json,1791497341.0649164,1 +v1annealC_120k_l0fix,polymath_pt_medium_cot,0,lm-eval,vllm,,think_closed,all,0.272,0.03489800807699396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/2da574a58b_2026-10-08T22-21-05.902343.json,1791497341.0649164,1 +v1annealC_120k_l0fix,polymath_pt_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/08276924d8_2026-10-08T22-21-08.674674.json,1791497337.9904022,1 +v1annealC_120k_l0fix,polymath_pt_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/08276924d8_2026-10-08T22-21-08.674674.json,1791497337.9904022,1 +v1annealC_120k_l0fix,polymath_pt_top_cot,0,lm-eval,vllm,,think_closed,all,0.032,0.012370620763103043,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_120k_l0fix/cot/2026-10-09-00-05-19/results/08276924d8_2026-10-08T22-21-08.674674.json,1791497337.9904022,1 diff --git a/results/v1annealC_merge3_116k_120k.flag-evals-471.tasks.csv b/results/v1annealC_merge3_116k_120k.flag-evals-471.tasks.csv new file mode 100644 index 0000000..f8c5139 --- /dev/null +++ b/results/v1annealC_merge3_116k_120k.flag-evals-471.tasks.csv @@ -0,0 +1,2124 @@ +checkpoint,task,n_shot,harness,backend,is_group,metric,filter,value,stderr,n_samples,results_file,result_time,n_files +v1annealC_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,accuracy_avg,,0.0,0.0,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a9a9e740f/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-16-27.587810.json,1791389783.0165303,1 +v1annealC_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,solved_avg,,0.0,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a9a9e740f/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-16-27.587810.json,1791389783.0165303,1 +v1annealC_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,accuracy_avg,,0.0,0.0,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/73b8403f80/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-30-52.343213.json,1791390647.3535817,1 +v1annealC_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,solved_avg,,0.0,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/73b8403f80/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-30-52.343213.json,1791390647.3535817,1 +v1annealC_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,accuracy_avg,,0.07999999999999999,0.0031622776601683803,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/68db9c80a1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-07-09.190490.json,1791389225.1379607,1 +v1annealC_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,solved_avg,,3.2,,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/68db9c80a1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-07-09.190490.json,1791389225.1379607,1 +v1annealC_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,accuracy_avg,,0.2878787878787879,0.010377801351799632,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/36c114f96d/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-12-39.639557.json,1791389555.3453999,1 +v1annealC_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,solved_avg,,57.0,,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/36c114f96d/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-12-39.639557.json,1791389555.3453999,1 +v1annealC_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,python_pass@1,,0.17682926829268292,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/30c06714df/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-18-48.416082.json,1791389924.7871711,1 +v1annealC_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,sh_pass@1,,0.012658227848101266,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/30c06714df/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-18-48.416082.json,1791389924.7871711,1 +v1annealC_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,accuracy_avg,,0.12135922330097088,0.001981787817785742,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f0654759cf/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-23-11.310087.json,1791390186.6856086,1 +v1annealC_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,solved_avg,,62.5,,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f0654759cf/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-23-11.310087.json,1791390186.6856086,1 +v1annealC_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_avg,,0.0182648401826484,0.0018679479534607117,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ccc9987cdc/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T17-02-10.296805.json,1791392526.5800524,1 +v1annealC_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_easy_avg,,0.04578754578754579,0.00463337386105257,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ccc9987cdc/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T17-02-10.296805.json,1791392526.5800524,1 +v1annealC_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_hard_avg,,0.0,0.0,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ccc9987cdc/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T17-02-10.296805.json,1791392526.5800524,1 +v1annealC_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_medium_avg,,0.004854368932038834,0.0012533926686755393,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ccc9987cdc/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T17-02-10.296805.json,1791392526.5800524,1 +v1annealC_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,solved_avg,,9.333333333333334,,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ccc9987cdc/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T17-02-10.296805.json,1791392526.5800524,1 +v1annealC_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,accuracy,,0.222,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b598fa49ef/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-06-41.098271.json,1791389193.3087819,1 +v1annealC_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,num_solved,,111,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b598fa49ef/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealC_merge3_116k_120k/results_2026-10-07T16-06-41.098271.json,1791389193.3087819,1 +v1annealC_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc,none,0.30869565217391304,0.030526861712901036,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a1be1e2de0_2026-10-07T15-38-36.169943.json,1791387347.2727866,1 +v1annealC_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc_norm,none,0.2826086956521739,0.02975452853823324,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a1be1e2de0_2026-10-07T15-38-36.169943.json,1791387347.2727866,1 +v1annealC_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc,none,0.6049488054607508,0.014285898292938231,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5ab5616fbf_2026-10-07T16-21-55.173220.json,1791389927.6082423,1 +v1annealC_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc_norm,none,0.6356655290102389,0.014063260279882469,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5ab5616fbf_2026-10-07T16-21-55.173220.json,1791389927.6082423,1 +v1annealC_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc,none,0.6143344709897611,0.014224250973257123,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f3678a4d9e_2026-10-07T16-16-34.658258.json,1791389558.9979486,1 +v1annealC_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc_norm,none,0.64419795221843,0.01399057113791884,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f3678a4d9e_2026-10-07T16-16-34.658258.json,1791389558.9979486,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc,none,0.5315699658703071,0.014582236460866984,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09628f106e_2026-10-07T16-02-35.483847.json,1791388710.6136544,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc_norm,none,0.5588737201365188,0.014509747749064824,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09628f106e_2026-10-07T16-02-35.483847.json,1791388710.6136544,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc,none,0.5426621160409556,0.014558106543923992,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f7c29eec90_2026-10-07T15-49-55.735001.json,1791387964.8040493,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc_norm,none,0.5614334470989761,0.014500682618212822,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f7c29eec90_2026-10-07T15-49-55.735001.json,1791387964.8040493,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc,none,0.5307167235494881,0.014583792546304033,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aa29f0be88_2026-10-07T15-51-58.681713.json,1791388088.8384068,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc_norm,none,0.5699658703071673,0.01446763155913799,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aa29f0be88_2026-10-07T15-51-58.681713.json,1791388088.8384068,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc,none,0.5110921501706485,0.014607794914013027,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/737d3627f8_2026-10-07T15-39-45.727529.json,1791387355.092296,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc_norm,none,0.5435153583617748,0.014555949760496543,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/737d3627f8_2026-10-07T15-39-45.727529.json,1791387355.092296,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc,none,0.5110921501706485,0.014607794914013027,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/34eef83f53_2026-10-07T16-06-42.331482.json,1791388948.4901304,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc_norm,none,0.53839590443686,0.014568245550296302,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/34eef83f53_2026-10-07T16-06-42.331482.json,1791388948.4901304,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc,none,0.5452218430034129,0.014551507060836232,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9d42dac682_2026-10-07T16-28-58.221644.json,1791390304.5256374,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc_norm,none,0.5853242320819113,0.014397070564409184,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9d42dac682_2026-10-07T16-28-58.221644.json,1791390304.5256374,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc,none,0.4880546075085324,0.014607220340597225,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e2c74b45e_2026-10-07T15-39-46.842961.json,1791387348.868914,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc_norm,none,0.5213310580204779,0.014598087973127125,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e2c74b45e_2026-10-07T15-39-46.842961.json,1791387348.868914,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc,none,0.48208191126279865,0.014602005585490881,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/273aa2f057_2026-10-07T16-04-14.744957.json,1791388823.549404,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc_norm,none,0.5221843003412969,0.014597001927076213,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/273aa2f057_2026-10-07T16-04-14.744957.json,1791388823.549404,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc,none,0.5426621160409556,0.014558106543923992,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f2a2deccba_2026-10-07T16-04-40.367837.json,1791388838.5731938,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc_norm,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f2a2deccba_2026-10-07T16-04-40.367837.json,1791388838.5731938,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc,none,0.5,0.014611390804670088,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7a38a57c7c_2026-10-07T15-54-21.794144.json,1791388222.8640296,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc_norm,none,0.5443686006825939,0.014553749939306847,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7a38a57c7c_2026-10-07T15-54-21.794144.json,1791388222.8640296,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc,none,0.5,0.014611390804670088,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bbf2bb422e_2026-10-07T15-39-45.358379.json,1791387351.5835552,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc_norm,none,0.5366894197952219,0.014572000527756918,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bbf2bb422e_2026-10-07T15-39-45.358379.json,1791387351.5835552,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc,none,0.5460750853242321,0.014549221105171829,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d212085c8d_2026-10-07T15-39-35.155594.json,1791387347.129751,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc_norm,none,0.5938566552901023,0.014351656690097877,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d212085c8d_2026-10-07T15-39-35.155594.json,1791387347.129751,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc,none,0.5127986348122867,0.014606603181012609,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/259ededcf0_2026-10-07T16-04-17.597440.json,1791388825.894596,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc_norm,none,0.5392491467576792,0.014566303676636534,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/259ededcf0_2026-10-07T16-04-17.597440.json,1791388825.894596,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc,none,0.4616040955631399,0.014568245550296302,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2e737032e1_2026-10-07T16-16-54.964342.json,1791389557.4619176,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc_norm,none,0.48464163822525597,0.014604496129394757,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2e737032e1_2026-10-07T16-16-54.964342.json,1791389557.4619176,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc,none,0.5324232081911263,0.014580637569995414,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f61f2b31b9_2026-10-07T15-39-45.645007.json,1791387354.9567847,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc_norm,none,0.5742320819112628,0.014449464278868677,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f61f2b31b9_2026-10-07T15-39-45.645007.json,1791387354.9567847,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc,none,0.53839590443686,0.014568245550296302,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f923017105_2026-10-07T15-52-05.389927.json,1791388093.6568558,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc_norm,none,0.5648464163822525,0.014487986197186081,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f923017105_2026-10-07T15-52-05.389927.json,1791388093.6568558,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc,none,0.5366894197952219,0.014572000527756918,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/59f80b9273_2026-10-07T16-06-18.245905.json,1791388947.96069,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc_norm,none,0.552901023890785,0.01452938016052677,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/59f80b9273_2026-10-07T16-06-18.245905.json,1791388947.96069,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc,none,0.5477815699658704,0.014544519880633823,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6b5d12c0d9_2026-10-07T16-06-27.917549.json,1791388947.9909954,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc_norm,none,0.5895904436860068,0.014374922192642638,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6b5d12c0d9_2026-10-07T16-06-27.917549.json,1791388947.9909954,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc,none,0.5358361774744027,0.014573813664735622,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bea947199_2026-10-07T16-06-35.451225.json,1791388951.2451284,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc_norm,none,0.5554607508532423,0.014521226405627025,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bea947199_2026-10-07T16-06-35.451225.json,1791388951.2451284,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc,none,0.5247440273037542,0.014593487694937702,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e97fd4089c_2026-10-07T16-02-17.512688.json,1791388700.2455294,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc_norm,none,0.5597269624573379,0.014506769524804264,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e97fd4089c_2026-10-07T16-02-17.512688.json,1791388700.2455294,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc,none,0.5290102389078498,0.014586776355294413,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9630f7b3cc_2026-10-07T16-06-23.746273.json,1791388948.5604722,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc_norm,none,0.5503412969283277,0.014537144444284783,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9630f7b3cc_2026-10-07T16-06-23.746273.json,1791388948.5604722,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc,none,0.5298634812286689,0.014585305840007116,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a397a94046_2026-10-07T16-06-21.099058.json,1791388946.4391074,1 +v1annealC_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc_norm,none,0.5853242320819113,0.014397070564409184,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a397a94046_2026-10-07T16-06-21.099058.json,1791388946.4391074,1 +v1annealC_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc,none,0.8543771043771043,0.007237820779715655,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0fea0db258_2026-10-07T16-28-31.976843.json,1791390298.1802907,1 +v1annealC_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc_norm,none,0.8644781144781145,0.007023440574367747,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0fea0db258_2026-10-07T16-28-31.976843.json,1791390298.1802907,1 +v1annealC_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc,none,0.8744444444444445,0.011051067526018369,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8da35e0bbd_2026-10-07T16-19-49.944711.json,1791389806.4976788,1 +v1annealC_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc_norm,none,0.8744444444444445,0.011051067526018369,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8da35e0bbd_2026-10-07T16-19-49.944711.json,1791389806.4976788,1 +v1annealC_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc,none,0.8788888888888889,0.010881258692882334,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c82659701b_2026-10-07T16-23-58.895126.json,1791390056.8537738,1 +v1annealC_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc_norm,none,0.8788888888888889,0.010881258692882334,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c82659701b_2026-10-07T16-23-58.895126.json,1791390056.8537738,1 +v1annealC_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc,none,0.8811111111111111,0.010794589393035885,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a8b0b0c2e7_2026-10-07T16-03-22.843052.json,1791388826.240318,1 +v1annealC_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc_norm,none,0.8811111111111111,0.010794589393035885,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a8b0b0c2e7_2026-10-07T16-03-22.843052.json,1791388826.240318,1 +v1annealC_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc,none,0.8811111111111111,0.010794589393035885,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ce31332eb8_2026-10-07T15-51-15.407746.json,1791388095.2801502,1 +v1annealC_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc_norm,none,0.8811111111111111,0.010794589393035885,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ce31332eb8_2026-10-07T15-51-15.407746.json,1791388095.2801502,1 +v1annealC_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc,none,0.8677777777777778,0.011297351524647564,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f2bfadadbb_2026-10-07T15-48-59.366313.json,1791387963.026748,1 +v1annealC_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc_norm,none,0.8677777777777778,0.011297351524647564,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f2bfadadbb_2026-10-07T15-48-59.366313.json,1791387963.026748,1 +v1annealC_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc,none,0.88,0.010838074031893345,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e4f13bf45_2026-10-07T16-23-59.222299.json,1791390048.3014662,1 +v1annealC_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc_norm,none,0.88,0.010838074031893345,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e4f13bf45_2026-10-07T16-23-59.222299.json,1791390048.3014662,1 +v1annealC_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc,none,0.8444444444444444,0.012087833203630684,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7af0c2fa7c_2026-10-07T16-21-44.417226.json,1791389929.9756932,1 +v1annealC_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc_norm,none,0.8444444444444444,0.012087833203630684,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7af0c2fa7c_2026-10-07T16-21-44.417226.json,1791389929.9756932,1 +v1annealC_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc,none,0.8655555555555555,0.011377296040197065,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b76ce2846e_2026-10-07T15-47-12.403205.json,1791387858.5524018,1 +v1annealC_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc_norm,none,0.8655555555555555,0.011377296040197065,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b76ce2846e_2026-10-07T15-47-12.403205.json,1791387858.5524018,1 +v1annealC_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc,none,0.8666666666666667,0.011337454811236778,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f1420aa64c_2026-10-07T15-51-13.163259.json,1791388093.7732477,1 +v1annealC_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc_norm,none,0.8666666666666667,0.011337454811236778,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f1420aa64c_2026-10-07T15-51-13.163259.json,1791388093.7732477,1 +v1annealC_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc,none,0.8611111111111112,0.011534094424130552,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e81203b14c_2026-10-07T15-47-27.519388.json,1791387863.715913,1 +v1annealC_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc_norm,none,0.8611111111111112,0.011534094424130552,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e81203b14c_2026-10-07T15-47-27.519388.json,1791387863.715913,1 +v1annealC_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc,none,0.8533333333333334,0.011799000521176654,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9699ef89b5_2026-10-07T16-01-19.558318.json,1791388701.8479233,1 +v1annealC_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc_norm,none,0.8533333333333334,0.011799000521176654,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9699ef89b5_2026-10-07T16-01-19.558318.json,1791388701.8479233,1 +v1annealC_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc,none,0.8533333333333334,0.011799000521176654,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac08b6b388_2026-10-07T16-05-19.645293.json,1791388941.8235261,1 +v1annealC_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc_norm,none,0.8533333333333334,0.011799000521176654,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac08b6b388_2026-10-07T16-05-19.645293.json,1791388941.8235261,1 +v1annealC_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc,none,0.8644444444444445,0.011416877955019054,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bf6dda30c3_2026-10-07T15-42-59.158662.json,1791387599.6945963,1 +v1annealC_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc_norm,none,0.8644444444444445,0.011416877955019054,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bf6dda30c3_2026-10-07T15-42-59.158662.json,1791387599.6945963,1 +v1annealC_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc,none,0.8322222222222222,0.012462553256116676,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6fd5269853_2026-10-07T15-38-42.389740.json,1791387349.88211,1 +v1annealC_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc_norm,none,0.8322222222222222,0.012462553256116676,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6fd5269853_2026-10-07T15-38-42.389740.json,1791387349.88211,1 +v1annealC_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.012429507075907847,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1758974507_2026-10-07T15-53-11.738635.json,1791388218.3355458,1 +v1annealC_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc_norm,none,0.8333333333333334,0.012429507075907847,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1758974507_2026-10-07T15-53-11.738635.json,1791388218.3355458,1 +v1annealC_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc,none,0.8555555555555555,0.011724509515301441,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93d989ead2_2026-10-07T16-15-48.080611.json,1791389567.1236396,1 +v1annealC_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc_norm,none,0.8555555555555555,0.011724509515301441,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93d989ead2_2026-10-07T16-15-48.080611.json,1791389567.1236396,1 +v1annealC_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc,none,0.8588888888888889,0.011610990029640366,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/74053b526f_2026-10-07T16-17-50.189529.json,1791389692.1514428,1 +v1annealC_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc_norm,none,0.8588888888888889,0.011610990029640366,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/74053b526f_2026-10-07T16-17-50.189529.json,1791389692.1514428,1 +v1annealC_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc,none,0.8544444444444445,0.01176187236814472,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/964cd5f2fc_2026-10-07T15-47-19.171218.json,1791387854.4723961,1 +v1annealC_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc_norm,none,0.8544444444444445,0.01176187236814472,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/964cd5f2fc_2026-10-07T15-47-19.171218.json,1791387854.4723961,1 +v1annealC_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc,none,0.8744444444444445,0.011051067526018369,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b4e94280_2026-10-07T15-38-43.497476.json,1791387346.6388545,1 +v1annealC_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc_norm,none,0.8744444444444445,0.011051067526018369,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b4e94280_2026-10-07T15-38-43.497476.json,1791387346.6388545,1 +v1annealC_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc,none,0.8622222222222222,0.011495274539524399,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/19d2624493_2026-10-07T16-15-52.258580.json,1791389563.629175,1 +v1annealC_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc_norm,none,0.8622222222222222,0.011495274539524399,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/19d2624493_2026-10-07T16-15-52.258580.json,1791389563.629175,1 +v1annealC_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc,none,0.8588888888888889,0.011610990029640366,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6fc8991d42_2026-10-07T15-42-56.468975.json,1791387598.3169768,1 +v1annealC_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc_norm,none,0.8588888888888889,0.011610990029640366,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6fc8991d42_2026-10-07T15-42-56.468975.json,1791387598.3169768,1 +v1annealC_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc,none,0.8677777777777778,0.011297351524647564,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a28e28e15a_2026-10-07T15-47-18.144698.json,1791387858.1738622,1 +v1annealC_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc_norm,none,0.8677777777777778,0.011297351524647564,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a28e28e15a_2026-10-07T15-47-18.144698.json,1791387858.1738622,1 +v1annealC_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc,none,0.8666666666666667,0.011337454811236778,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/11d9db8902_2026-10-07T16-05-17.195417.json,1791388941.9462264,1 +v1annealC_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc_norm,none,0.8666666666666667,0.011337454811236778,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/11d9db8902_2026-10-07T16-05-17.195417.json,1791388941.9462264,1 +v1annealC_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc,none,0.8655555555555555,0.011377296040197065,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/96fab5f2a3_2026-10-07T15-49-04.840196.json,1791387968.085796,1 +v1annealC_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc_norm,none,0.8655555555555555,0.011377296040197065,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/96fab5f2a3_2026-10-07T15-49-04.840196.json,1791387968.085796,1 +v1annealC_merge3_116k_120k,bigbench_cs_algorithms_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.6878787878787879,0.012758370308859162,1320,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66cdf1d3b_2026-10-07T15-47-20.340705.json,1791387860.8247266,1 +v1annealC_merge3_116k_120k,bigbench_dyck_languages_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.371,0.01528373621182319,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a16fff8b91_2026-10-07T15-38-49.764498.json,1791387348.825079,1 +v1annealC_merge3_116k_120k,bigbench_language_identification_multiple_choice,10,lm-eval,vllm,,acc,none,0.1662,0.0037227868478052054,10000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fd777322e4_2026-10-07T16-46-38.139771.json,1791387969.2513282,1 +v1annealC_merge3_116k_120k,bigbench_operators_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7142857142857143,0.031248474232843364,210,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/031b26c3b1_2026-10-07T16-17-38.579481.json,1791389692.4673433,1 +v1annealC_merge3_116k_120k,bigbench_qa_wikidata_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7149746567590177,0.0031668333570594696,20321,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5c90208342_2026-10-07T16-05-18.518489.json,1791388827.917006,1 +v1annealC_merge3_116k_120k,bigbench_repeat_copy_logic_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.53125,0.08962708359030336,32,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4fc1efd82b_2026-10-07T16-17-26.037980.json,1791389684.3829253,1 +v1annealC_merge3_116k_120k,boolq,10,lm-eval,vllm,,acc,none,0.872782874617737,0.005827985153449986,3270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a7a10d871_2026-10-07T15-41-29.753950.json,1791387351.3814783,1 +v1annealC_merge3_116k_120k,commonsense_qa,10,lm-eval,vllm,,acc,none,0.7682227682227682,0.012080893552302395,1221,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a55ba7495d_2026-10-07T16-03-42.581966.json,1791388828.6941402,1 +v1annealC_merge3_116k_120k,copa,0,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a8c7fbac4_2026-10-07T16-15-18.791983.json,1791389565.9757826,1 +v1annealC_merge3_116k_120k,coqa,0,lm-eval,vllm,,em,none,0.6818333333333334,0.017272262474582495,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0426d9ee7a_2026-10-07T15-47-15.316040.json,1791387858.481762,1 +v1annealC_merge3_116k_120k,coqa,0,lm-eval,vllm,,f1,none,0.8075330061919089,0.012832284684182916,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0426d9ee7a_2026-10-07T15-47-15.316040.json,1791387858.481762,1 +v1annealC_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.94733990438015,0.017802161348392815,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b035bec5a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-28.393644.json,1791389609.43986,1 +v1annealC_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6779212296586663,0.003929234759911824,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b035bec5a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-28.393644.json,1791389609.43986,1 +v1annealC_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22660840286683184,0.005668892040431169,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b035bec5a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-28.393644.json,1791389609.43986,1 +v1annealC_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.56644539976672,0.012237525993707896,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b035bec5a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-28.393644.json,1791389609.43986,1 +v1annealC_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,41.5163701021105,0.01772916064748811,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d3f7537dc0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-34.522116.json,1791390575.78582,1 +v1annealC_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6856914619319576,0.0038239275728021967,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d3f7537dc0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-34.522116.json,1791390575.78582,1 +v1annealC_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.24108907377813982,0.005825870455503718,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d3f7537dc0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-34.522116.json,1791390575.78582,1 +v1annealC_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.05214375589473,0.011334339308165173,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d3f7537dc0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-34.522116.json,1791390575.78582,1 +v1annealC_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.95002379386645,0.017272363265507153,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0cabb372a8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-14.284701.json,1791389355.789241,1 +v1annealC_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6537169867057586,0.0041583813270631076,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0cabb372a8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-14.284701.json,1791389355.789241,1 +v1annealC_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20160026895201266,0.00549544117595596,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0cabb372a8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-14.284701.json,1791389355.789241,1 +v1annealC_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.81495310993116,0.011493731524015813,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0cabb372a8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-14.284701.json,1791389355.789241,1 +v1annealC_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.98804606906254,0.01938962590061186,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d845dbdd11/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-43.203731.json,1791389504.280046,1 +v1annealC_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7081326432726657,0.004056597825974734,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d845dbdd11/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-43.203731.json,1791389504.280046,1 +v1annealC_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2809560360195398,0.00648431148924039,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d845dbdd11/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-43.203731.json,1791389504.280046,1 +v1annealC_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.28000377375115,0.012839442995110471,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d845dbdd11/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-43.203731.json,1791389504.280046,1 +v1annealC_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.35749425277023,0.017999386348913838,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f4c2dd6b45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-31.929022.json,1791390573.092,1 +v1annealC_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6615495815087505,0.004113659361859519,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f4c2dd6b45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-31.929022.json,1791390573.092,1 +v1annealC_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21586488696641426,0.005795732125929918,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f4c2dd6b45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-31.929022.json,1791390573.092,1 +v1annealC_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.745183695383886,0.012495509353004247,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f4c2dd6b45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-31.929022.json,1791390573.092,1 +v1annealC_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.2217467898525,0.018815854427657396,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8b4fb77d9f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-09.495323.json,1791389470.54634,1 +v1annealC_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6931264065291651,0.004293117924974717,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8b4fb77d9f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-09.495323.json,1791389470.54634,1 +v1annealC_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.26469943231791204,0.006210477607485874,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8b4fb77d9f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-09.495323.json,1791389470.54634,1 +v1annealC_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.11180133545864,0.012258395239829934,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8b4fb77d9f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-09.495323.json,1791389470.54634,1 +v1annealC_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.263185199436904,0.019659994337379725,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/578f076118/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-04.304110.json,1791389465.099276,1 +v1annealC_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6771461961057034,0.004131044057576834,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/578f076118/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-04.304110.json,1791389465.099276,1 +v1annealC_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2307350654905579,0.006023344755052874,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/578f076118/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-04.304110.json,1791389465.099276,1 +v1annealC_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.14489330318189,0.013005849478424359,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/578f076118/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-04.304110.json,1791389465.099276,1 +v1annealC_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.68070056218005,0.01795399010364252,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/383d25e24d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-32.495005.json,1791389373.917986,1 +v1annealC_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6317136236848218,0.0042494793509929895,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/383d25e24d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-32.495005.json,1791389373.917986,1 +v1annealC_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18523883149956538,0.005282310671365189,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/383d25e24d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-32.495005.json,1791389373.917986,1 +v1annealC_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.49421245657324,0.013209227615529786,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/383d25e24d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-32.495005.json,1791389373.917986,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu,none,26.75334470046106,0.014652812303920156,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/85be226573/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-33.388342.json,1791389614.385175,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5713143331934731,0.0038043332032307187,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/85be226573/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-33.388342.json,1791389614.385175,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12170145180361062,0.004142291394689329,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/85be226573/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-33.388342.json,1791389614.385175,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.51697974535461,0.010475805095852154,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/85be226573/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-33.388342.json,1791389614.385175,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu,none,30.203068298979215,0.016809290051522513,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/20a98babf3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-44.305082.json,1791390585.160363,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5830593099031629,0.004554864561100393,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/20a98babf3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-44.305082.json,1791390585.160363,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.15271733671745308,0.004721811304231831,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/20a98babf3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-44.305082.json,1791390585.160363,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.12429854482111,0.012092911595439893,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/20a98babf3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-44.305082.json,1791390585.160363,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu,none,39.34179999010887,0.017713378358845015,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/35bc98f3f7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-17.841624.json,1791389418.649595,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6526802402704809,0.0040153629104897354,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/35bc98f3f7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-17.841624.json,1791389418.649595,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.21741944734625776,0.005314231934666996,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/35bc98f3f7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-17.841624.json,1791389418.649595,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,63.70601733662821,0.012176118802686159,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/35bc98f3f7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-17.841624.json,1791389418.649595,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu,none,41.6957626834798,0.01742171596616026,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/187793f95c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-57.486069.json,1791389518.425737,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6623436220216699,0.00419288247458202,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/187793f95c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-57.486069.json,1791389518.425737,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.250098085620977,0.005847363742191826,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/187793f95c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-57.486069.json,1791389518.425737,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.20321700441451,0.01249142998761472,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/187793f95c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-57.486069.json,1791389518.425737,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu,none,32.34735912091763,0.019589025107058542,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/27e6a0168e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-02.323730.json,1791389463.536859,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5924088987132899,0.00489210180817672,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/27e6a0168e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-02.323730.json,1791389463.536859,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16902775032381157,0.005757824624509422,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/27e6a0168e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-02.323730.json,1791389463.536859,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.96492579425833,0.0142182306345264,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/27e6a0168e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-02.323730.json,1791389463.536859,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu,none,45.91282996841182,0.0194046576872795,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2edcd144bf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-26.321189.json,1791389547.308829,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6964731428229348,0.004522852874699928,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2edcd144bf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-26.321189.json,1791389547.308829,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29629500829036626,0.00698626404150007,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2edcd144bf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-26.321189.json,1791389547.308829,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.9196660237092,0.012693075336554076,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2edcd144bf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-26.321189.json,1791389547.308829,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu,none,37.25050649986385,0.02045169169230887,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5608f6cbbe/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-23.439668.json,1791389484.70853,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6304808191043422,0.004722908097462551,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5608f6cbbe/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-23.439668.json,1791389484.70853,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21261270650827394,0.006000003739438492,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5608f6cbbe/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-23.439668.json,1791389484.70853,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.27834262031307,0.013752598337003707,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5608f6cbbe/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-23.439668.json,1791389484.70853,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu,none,26.197304264927407,0.015323934713139288,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1984d82c36/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-40.364052.json,1791389441.492449,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_1,none,0.5339997753173484,0.004416132985903739,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1984d82c36/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-40.364052.json,1791389441.492449,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_4,none,0.12135001789711515,0.004142430358967289,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1984d82c36/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-40.364052.json,1791389441.492449,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,chrf++,rescored,51.31120795122497,0.012258045075849081,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1984d82c36/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-40.364052.json,1791389441.492449,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu,none,26.393228841802276,0.018406787832067256,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5f047a4249/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-48.430413.json,1791390589.545411,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5490107710943769,0.004988885339830443,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5f047a4249/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-48.430413.json,1791390589.545411,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12296570188938204,0.005058225855649347,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5f047a4249/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-48.430413.json,1791390589.545411,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.71063551458647,0.012705170667614101,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5f047a4249/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-48.430413.json,1791390589.545411,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu,none,17.79439551489284,0.015596969754243486,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/548cafdeed/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-08.160431.json,1791389528.940552,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.47795650637556525,0.004578744299107078,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/548cafdeed/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-08.160431.json,1791389528.940552,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.06757026938301919,0.0036656801557742916,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/548cafdeed/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-08.160431.json,1791389528.940552,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,51.75777821982751,0.011448080996768967,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/548cafdeed/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-08.160431.json,1791389528.940552,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu,none,23.742718364041185,0.01951997689943873,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67260c8bd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-41.492060.json,1791389562.581165,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5138512149079411,0.00507914311584143,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67260c8bd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-41.492060.json,1791389562.581165,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.10722911588282295,0.004795278794127177,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67260c8bd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-41.492060.json,1791389562.581165,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.44816773343892,0.013158198481872854,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67260c8bd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-41.492060.json,1791389562.581165,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu,none,44.73596795991678,0.02170517231421081,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cc43d12aea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-51.233961.json,1791389512.358196,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6674235693178234,0.004932862887197091,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cc43d12aea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-51.233961.json,1791389512.358196,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29499385864653055,0.007216318346738838,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cc43d12aea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-51.233961.json,1791389512.358196,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.26702823179525,0.014771255032399025,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cc43d12aea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-51.233961.json,1791389512.358196,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu,none,31.159639634580337,0.018323077467137256,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b68fb8ec5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-37.158008.json,1791389558.558197,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5792765491457132,0.004434340426168555,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b68fb8ec5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-37.158008.json,1791389558.558197,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.15932862255234687,0.004934217141725651,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b68fb8ec5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-37.158008.json,1791389558.558197,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.632571817373986,0.013032853050585751,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b68fb8ec5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-37.158008.json,1791389558.558197,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu,none,34.98739526338918,0.01594355724441695,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/90299840a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-27.807061.json,1791389549.307286,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6216781747730867,0.003925500141876096,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/90299840a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-27.807061.json,1791389549.307286,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.19086642676695598,0.005160674037455537,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/90299840a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-27.807061.json,1791389549.307286,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.81035973235114,0.011357231908594717,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/90299840a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-27.807061.json,1791389549.307286,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu,none,30.57914232174979,0.01792787257373687,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/29c4d2cafa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.093577.json,1791389478.919118,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5669258964669225,0.005143799096138726,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/29c4d2cafa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.093577.json,1791389478.919118,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.15820734336460598,0.005313073398760333,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/29c4d2cafa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.093577.json,1791389478.919118,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.94632506676997,0.013405949424676345,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/29c4d2cafa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.093577.json,1791389478.919118,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu,none,23.562349995854756,0.02072138137220983,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c6765b760b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-44.173942.json,1791389625.382628,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5429932200046328,0.004574353181243526,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c6765b760b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-44.173942.json,1791389625.382628,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.10439916512107499,0.004243014567904729,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c6765b760b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-44.173942.json,1791389625.382628,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,53.67375576266542,0.01266806415767421,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c6765b760b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-44.173942.json,1791389625.382628,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu,none,27.267069524735696,0.01840188632418441,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17ce35aa1e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-50.432433.json,1791389391.224051,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5322450092479906,0.0048986378655833515,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17ce35aa1e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-50.432433.json,1791389391.224051,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.13320525079502682,0.005276663463881642,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17ce35aa1e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-50.432433.json,1791389391.224051,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,52.226833004792596,0.01364411754476437,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17ce35aa1e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-50.432433.json,1791389391.224051,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu,none,30.330853097551042,0.015527470464588009,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/07206658c1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-31.507379.json,1791389432.622442,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5793392599061601,0.003851458772884867,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/07206658c1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-31.507379.json,1791389432.622442,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.14679278021150957,0.00410567914251124,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/07206658c1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-31.507379.json,1791389432.622442,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.705667040675955,0.010633919726706796,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/07206658c1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-31.507379.json,1791389432.622442,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu,none,0.341684245756248,0.0035883769251573642,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d3a1cf5960/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-43-49.263854.json,1791391430.249221,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_1,none,0.046173912943226036,0.0020435859335891705,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d3a1cf5960/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-43-49.263854.json,1791391430.249221,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_4,none,0.0007201942663112809,0.0005169421560965357,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d3a1cf5960/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-43-49.263854.json,1791391430.249221,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,chrf++,rescored,11.701670695273428,0.0054637297842684346,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d3a1cf5960/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-43-49.263854.json,1791391430.249221,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu,none,25.153445510626174,0.018586535576709348,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/72216eeb41/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-14-01.385297.json,1791389642.584292,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5349075936572212,0.004889117015046102,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/72216eeb41/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-14-01.385297.json,1791389642.584292,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11466396453327436,0.004855968785997692,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/72216eeb41/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-14-01.385297.json,1791389642.584292,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.23604553923994,0.013062756989675826,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/72216eeb41/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-14-01.385297.json,1791389642.584292,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu,none,25.626609459579626,0.017853075671149157,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6cbf4cfb57/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-36.371837.json,1791389617.448974,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.544859835437259,0.00508120630977892,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6cbf4cfb57/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-36.371837.json,1791389617.448974,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12008153464355059,0.0051918381967841305,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6cbf4cfb57/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-36.371837.json,1791389617.448974,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.07402822390366,0.013861740794930803,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6cbf4cfb57/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-13-36.371837.json,1791389617.448974,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu,none,35.37078647486028,0.01648450160884736,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e6c3673018/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-46.846444.json,1791389387.687216,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6272798651571306,0.003924024312770039,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e6c3673018/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-46.846444.json,1791389387.687216,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.18847542533285092,0.004993109869921781,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e6c3673018/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-46.846444.json,1791389387.687216,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,61.60203531382267,0.011180317046039192,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e6c3673018/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-46.846444.json,1791389387.687216,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu,none,36.9738418703264,0.019135652826177046,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b04dc83f6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-11.092405.json,1791390672.145196,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6275140080459681,0.004678156609249474,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b04dc83f6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-11.092405.json,1791390672.145196,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21154662583539466,0.006122202042766504,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b04dc83f6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-11.092405.json,1791390672.145196,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.54407599582036,0.013273657758322913,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b04dc83f6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-11.092405.json,1791390672.145196,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu,none,26.944208624172933,0.01601097491024317,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/089c2741f0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-45.466006.json,1791389386.51059,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5676923858671213,0.0043316343355356635,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/089c2741f0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-45.466006.json,1791389386.51059,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1219969132995103,0.004434099424937799,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/089c2741f0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-45.466006.json,1791389386.51059,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.161412831443776,0.01135984298937611,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/089c2741f0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-45.466006.json,1791389386.51059,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu,none,34.23063652739566,0.016182213937750163,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8a55c1c982/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-10.814972.json,1791389351.921979,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6115398162029737,0.0038399517151787247,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8a55c1c982/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-10.814972.json,1791389351.921979,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1681214872461737,0.0047391999562356995,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8a55c1c982/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-10.814972.json,1791389351.921979,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.78835148408431,0.01121924245007024,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8a55c1c982/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-10.814972.json,1791389351.921979,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu,none,21.954145764949555,0.01630749299603763,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e4e5ec38ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-10.066330.json,1791389410.994685,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.49493192898409505,0.0045589581912744825,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e4e5ec38ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-10.066330.json,1791389410.994685,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.09303982912013753,0.003840815810555899,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e4e5ec38ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-10.066330.json,1791389410.994685,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,48.91976365719163,0.012384886851791189,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e4e5ec38ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-10.066330.json,1791389410.994685,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu,none,45.90637782470985,0.02039974706067122,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/790b9e1dd0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-31.581106.json,1791389492.744801,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7017900093068109,0.004467945600871849,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/790b9e1dd0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-31.581106.json,1791389492.744801,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29570155153874594,0.006998644204168786,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/790b9e1dd0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-31.581106.json,1791389492.744801,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.68431493908795,0.013609668498785272,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/790b9e1dd0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-31.581106.json,1791389492.744801,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu,none,38.39087991743535,0.018513226889261606,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cd5c278e9b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-05.837262.json,1791389406.692085,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6372206382024007,0.004438248816105926,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cd5c278e9b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-05.837262.json,1791389406.692085,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22899763938772721,0.006084608869568464,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cd5c278e9b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-05.837262.json,1791389406.692085,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.7050605160594,0.012736481690484094,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cd5c278e9b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-10-05.837262.json,1791389406.692085,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu,none,32.87554382058287,0.020981616579500702,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1953bcd901/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-52.233983.json,1791389513.237414,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5891970791229368,0.005277327132796036,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1953bcd901/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-52.233983.json,1791389513.237414,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1793965386261008,0.006153863189241554,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1953bcd901/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-52.233983.json,1791389513.237414,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.596178396588314,0.014668725247856614,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1953bcd901/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-52.233983.json,1791389513.237414,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu,none,30.708514737583037,0.018256610259469116,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9926f105eb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-54.667898.json,1791390715.504699,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5768599683632697,0.004920862729661895,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9926f105eb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-54.667898.json,1791390715.504699,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16132955222933215,0.00534899831298906,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9926f105eb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-54.667898.json,1791390715.504699,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.77811611430419,0.013365053424775569,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9926f105eb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-54.667898.json,1791390715.504699,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu,none,27.288072562015834,0.012823363174961256,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bf8cf82fc7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-39-09.457242.json,1791391150.718425,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5601783236458903,0.0035048105603903965,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bf8cf82fc7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-39-09.457242.json,1791391150.718425,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12367602171239779,0.0034722308978069887,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bf8cf82fc7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-39-09.457242.json,1791391150.718425,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,53.60944766027805,0.009714122853825738,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bf8cf82fc7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-39-09.457242.json,1791391150.718425,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu,none,34.23765702831048,0.019514604590918173,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/689b16ddb8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-28.624541.json,1791389550.070883,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.609661458705923,0.0047722750474401155,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/689b16ddb8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-28.624541.json,1791389550.070883,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.18746390747427868,0.005635565975624403,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/689b16ddb8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-28.624541.json,1791389550.070883,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,58.9933302842003,0.013562825402997292,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/689b16ddb8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-28.624541.json,1791389550.070883,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu,none,43.60960276018088,0.019294020030004994,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c4d020b1b8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.500138.json,1791389479.293864,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6747808341840832,0.004369972342490486,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c4d020b1b8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.500138.json,1791389479.293864,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2666996866956336,0.006481472497867581,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c4d020b1b8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.500138.json,1791389479.293864,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.54413558445344,0.012756510143886539,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c4d020b1b8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.500138.json,1791389479.293864,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu,none,22.8885400014651,0.017661295878541608,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c41df0878a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-20.980013.json,1791389482.092486,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5235666052574554,0.004967850798193032,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c41df0878a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-20.980013.json,1791389482.092486,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.10185714921346879,0.004643321819914261,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c41df0878a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-20.980013.json,1791389482.092486,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,53.72285710982347,0.013517357246213571,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c41df0878a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-20.980013.json,1791389482.092486,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu,none,27.625777388893994,0.01719160104223163,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ceed8b2ea9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-46.675766.json,1791389567.705261,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.5402732785383441,0.004859938229708573,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ceed8b2ea9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-46.675766.json,1791389567.705261,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.13011795963533132,0.004486593068942084,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ceed8b2ea9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-46.675766.json,1791389567.705261,1 +v1annealC_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,54.03950542658712,0.012355372693975845,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ceed8b2ea9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-46.675766.json,1791389567.705261,1 +v1annealC_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.731569211458044,0.01862364389118325,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/adbd1a2566/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-54.222135.json,1791390595.922705,1 +v1annealC_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6582103581773057,0.004225662937442683,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/adbd1a2566/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-54.222135.json,1791390595.922705,1 +v1annealC_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21077612084594288,0.005943645998104579,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/adbd1a2566/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-54.222135.json,1791390595.922705,1 +v1annealC_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.546218499618575,0.012823496412833538,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/adbd1a2566/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-54.222135.json,1791390595.922705,1 +v1annealC_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,29.403320527099094,0.01713196236186623,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/877ad03469/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-29.729378.json,1791389490.886887,1 +v1annealC_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5910983851922863,0.00445852844108494,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/877ad03469/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-29.729378.json,1791389490.886887,1 +v1annealC_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.14934095786102922,0.004867858239375085,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/877ad03469/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-29.729378.json,1791389490.886887,1 +v1annealC_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.42701747215418,0.013196851845413396,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/877ad03469/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-29.729378.json,1791389490.886887,1 +v1annealC_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.904226526568706,0.017413073706713373,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6af63e6e09/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-23.019170.json,1791389484.509867,1 +v1annealC_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6318714500206882,0.004237863659864436,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6af63e6e09/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-23.019170.json,1791389484.509867,1 +v1annealC_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18012064301230776,0.005350909303351834,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6af63e6e09/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-23.019170.json,1791389484.509867,1 +v1annealC_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.98789027938477,0.012314994283915158,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6af63e6e09/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-23.019170.json,1791389484.509867,1 +v1annealC_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.00178245107052,0.020811543463115867,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3825c10c0e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-49.819375.json,1791390591.047275,1 +v1annealC_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6788231459110637,0.004491687891159758,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3825c10c0e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-49.819375.json,1791390591.047275,1 +v1annealC_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.24556267796014883,0.006419314311549751,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3825c10c0e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-49.819375.json,1791390591.047275,1 +v1annealC_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.38640603184422,0.01427926705430814,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3825c10c0e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-49.819375.json,1791390591.047275,1 +v1annealC_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,42.07839258218965,0.01956344878519709,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f977d72105/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.783139.json,1791389480.246252,1 +v1annealC_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6839488478445119,0.004433668154147187,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f977d72105/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.783139.json,1791389480.246252,1 +v1annealC_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.26086228934838535,0.0067214973442770035,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f977d72105/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.783139.json,1791389480.246252,1 +v1annealC_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.58847270213982,0.013306032732184244,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f977d72105/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-18.783139.json,1791389480.246252,1 +v1annealC_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.22301838494922,0.01792567208210065,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17878e3765/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-52.771886.json,1791389513.637555,1 +v1annealC_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6681326698591527,0.003977969824572511,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17878e3765/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-52.771886.json,1791389513.637555,1 +v1annealC_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22134982360615782,0.005860643793568513,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17878e3765/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-52.771886.json,1791389513.637555,1 +v1annealC_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.49233815065779,0.011581730039600044,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17878e3765/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-52.771886.json,1791389513.637555,1 +v1annealC_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.36544976325193,0.018716324919265337,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0b3a8194f7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-10.007971.json,1791389470.983823,1 +v1annealC_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6588581206902394,0.004160469170869128,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0b3a8194f7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-10.007971.json,1791389470.983823,1 +v1annealC_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21289042495640983,0.005885730711280091,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0b3a8194f7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-10.007971.json,1791389470.983823,1 +v1annealC_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.87039251791883,0.012896983640227441,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0b3a8194f7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-10.007971.json,1791389470.983823,1 +v1annealC_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,35.345364539544995,0.017815728335764412,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8af539ac5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-50.133190.json,1791390591.665824,1 +v1annealC_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6380038277073701,0.004346187013273859,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8af539ac5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-50.133190.json,1791390591.665824,1 +v1annealC_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.192685559030165,0.005579093602790042,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8af539ac5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-50.133190.json,1791390591.665824,1 +v1annealC_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.81670777562274,0.012330988829462427,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8af539ac5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-50.133190.json,1791390591.665824,1 +v1annealC_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.57176083099161,0.018895411743928503,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8edf3e42b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-32-15.219643.json,1791390736.284851,1 +v1annealC_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6394703284323736,0.004427531197817779,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8edf3e42b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-32-15.219643.json,1791390736.284851,1 +v1annealC_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2021703998452174,0.005868111756234877,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8edf3e42b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-32-15.219643.json,1791390736.284851,1 +v1annealC_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.19296341559305,0.013563339896747965,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8edf3e42b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-32-15.219643.json,1791390736.284851,1 +v1annealC_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,32.79932090826784,0.01572970255295126,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/879795ffaa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-13.046224.json,1791389474.178985,1 +v1annealC_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6267355149490065,0.003936699381991524,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/879795ffaa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-13.046224.json,1791389474.178985,1 +v1annealC_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17071878051631978,0.0046912757131525274,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/879795ffaa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-13.046224.json,1791389474.178985,1 +v1annealC_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.51392500498619,0.01135946676063386,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/879795ffaa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-13.046224.json,1791389474.178985,1 +v1annealC_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,1.8321163435108705,0.005659623334094782,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2e778f07e3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-36-41.917444.json,1791391002.921437,1 +v1annealC_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.19094252786351718,0.0028864741668656146,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2e778f07e3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-36-41.917444.json,1791391002.921437,1 +v1annealC_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.0031724782933204576,0.0006422836119358194,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2e778f07e3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-36-41.917444.json,1791391002.921437,1 +v1annealC_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,18.825370976265994,0.006788264669320647,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2e778f07e3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-36-41.917444.json,1791391002.921437,1 +v1annealC_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.638975835514245,0.017725180603020856,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1c88926d45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-58.420968.json,1791389519.504341,1 +v1annealC_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6175419328685731,0.004413479979920551,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1c88926d45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-58.420968.json,1791389519.504341,1 +v1annealC_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17817120682526155,0.005452524368365644,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1c88926d45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-58.420968.json,1791389519.504341,1 +v1annealC_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.854629268115644,0.013154388251981725,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1c88926d45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-58.420968.json,1791389519.504341,1 +v1annealC_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,35.47696997984112,0.02001593287243019,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3c2c585e7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-30.260463.json,1791389551.524549,1 +v1annealC_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6340010333472295,0.004538820139314285,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3c2c585e7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-30.260463.json,1791389551.524549,1 +v1annealC_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.19032936516546528,0.005474872700805728,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3c2c585e7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-30.260463.json,1791389551.524549,1 +v1annealC_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.7320260805476,0.014044158878689688,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3c2c585e7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-30.260463.json,1791389551.524549,1 +v1annealC_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.26491510941074,0.018258085372198064,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e1e5650838/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-48.194305.json,1791390709.024803,1 +v1annealC_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6720364282121303,0.004043504359264398,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e1e5650838/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-48.194305.json,1791390709.024803,1 +v1annealC_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23133911910460034,0.005844731363424379,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e1e5650838/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-48.194305.json,1791390709.024803,1 +v1annealC_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.0209759796328,0.012259136479134791,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e1e5650838/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-31-48.194305.json,1791390709.024803,1 +v1annealC_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,49.998118864238656,0.019606786470429786,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/52d1136c33/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-30-03.654336.json,1791390604.828525,1 +v1annealC_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7236637260210229,0.0043110269808994935,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/52d1136c33/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-30-03.654336.json,1791390604.828525,1 +v1annealC_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3336108806295953,0.007029448481288899,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/52d1136c33/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-30-03.654336.json,1791390604.828525,1 +v1annealC_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.68545910098113,0.012579674955734421,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/52d1136c33/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-30-03.654336.json,1791390604.828525,1 +v1annealC_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,31.689906578510673,0.01725425385467055,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6b3ae77c35/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-38.460572.json,1791389379.596826,1 +v1annealC_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6059873652515502,0.004270606732831394,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6b3ae77c35/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-38.460572.json,1791389379.596826,1 +v1annealC_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.15816883602774104,0.004990272413625464,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6b3ae77c35/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-38.460572.json,1791389379.596826,1 +v1annealC_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.894582909738816,0.012652816645827817,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6b3ae77c35/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-38.460572.json,1791389379.596826,1 +v1annealC_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,42.616346168360224,0.017875510232328078,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0ff95b2ffd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-04.694719.json,1791389465.765729,1 +v1annealC_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6816694186938882,0.004057504339238155,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0ff95b2ffd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-04.694719.json,1791389465.765729,1 +v1annealC_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.24922159430379567,0.005965654837586608,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0ff95b2ffd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-04.694719.json,1791389465.765729,1 +v1annealC_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.68682311611713,0.012384803155112029,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0ff95b2ffd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-04.694719.json,1791389465.765729,1 +v1annealC_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,29.213390761807897,0.016933611502127396,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c8cb2f55ed/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-14-09.636711.json,1791389650.90223,1 +v1annealC_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5925865380193065,0.004342979200734806,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c8cb2f55ed/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-14-09.636711.json,1791389650.90223,1 +v1annealC_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.14173021361406662,0.004776265136855723,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c8cb2f55ed/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-14-09.636711.json,1791389650.90223,1 +v1annealC_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.30051038843307,0.012460700296302417,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c8cb2f55ed/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-14-09.636711.json,1791389650.90223,1 +v1annealC_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.95814836761527,0.0189514843282576,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d39168e0b4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-11.731951.json,1791389472.90889,1 +v1annealC_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7101701267504016,0.004199680588209345,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d39168e0b4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-11.731951.json,1791389472.90889,1 +v1annealC_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28021560457897104,0.006398719889999115,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d39168e0b4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-11.731951.json,1791389472.90889,1 +v1annealC_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.94934085583984,0.012661909456127066,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d39168e0b4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-11.731951.json,1791389472.90889,1 +v1annealC_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.97725992184204,0.017967279894314635,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/645fccb8e3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-24.886128.json,1791389485.703691,1 +v1annealC_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6746073305605721,0.004215819301249751,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/645fccb8e3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-24.886128.json,1791389485.703691,1 +v1annealC_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23154793317786393,0.006020006354861041,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/645fccb8e3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-24.886128.json,1791389485.703691,1 +v1annealC_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.56906323312259,0.011961877632762574,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/645fccb8e3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-24.886128.json,1791389485.703691,1 +v1annealC_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.06272942539163,0.019354698989344235,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d6a0264718/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-39.240914.json,1791390580.797497,1 +v1annealC_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6674080296712039,0.004256616659025601,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d6a0264718/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-39.240914.json,1791390580.797497,1 +v1annealC_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2210405057800235,0.005999082169691368,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d6a0264718/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-39.240914.json,1791390580.797497,1 +v1annealC_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.0642030930844,0.012924348590632172,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d6a0264718/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-39.240914.json,1791390580.797497,1 +v1annealC_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,35.41509101908253,0.017806535651631566,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fe313a34f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-49.310720.json,1791389390.4194,1 +v1annealC_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6420261467743865,0.004169033845087484,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fe313a34f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-49.310720.json,1791389390.4194,1 +v1annealC_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.19228677652170037,0.005515878360751368,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fe313a34f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-49.310720.json,1791389390.4194,1 +v1annealC_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.85863385118695,0.012700670922272124,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fe313a34f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-49.310720.json,1791389390.4194,1 +v1annealC_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,29.53401441103537,0.0160518825200843,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/005d980119/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-27.998144.json,1791389549.503912,1 +v1annealC_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5976019437530412,0.004034911228091313,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/005d980119/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-27.998144.json,1791389549.503912,1 +v1annealC_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.14428173232417094,0.0045662596179040825,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/005d980119/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-27.998144.json,1791389549.503912,1 +v1annealC_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.85675903081046,0.011468583801405282,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/005d980119/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-12-27.998144.json,1791389549.503912,1 +v1annealC_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,41.5990336789783,0.01820938506831812,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5573352475/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-17.898193.json,1791389358.73662,1 +v1annealC_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6855872519579543,0.004215540689455278,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5573352475/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-17.898193.json,1791389358.73662,1 +v1annealC_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.24821680840498977,0.00634989201783135,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5573352475/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-17.898193.json,1791389358.73662,1 +v1annealC_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.11157758329651,0.011944073374147312,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5573352475/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-17.898193.json,1791389358.73662,1 +v1annealC_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,48.08574212784034,0.018806869421599155,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a21c7520da/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-03.507033.json,1791389344.563716,1 +v1annealC_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7270995662124413,0.003930887166680286,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a21c7520da/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-03.507033.json,1791389344.563716,1 +v1annealC_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3089640914039023,0.006530874321096774,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a21c7520da/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-03.507033.json,1791389344.563716,1 +v1annealC_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.66593551179086,0.012707296713613689,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a21c7520da/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-09-03.507033.json,1791389344.563716,1 +v1annealC_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,35.908726856281014,0.01775318903041035,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9282f1d881/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-24.594687.json,1791389485.977891,1 +v1annealC_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6437589794809292,0.004466919119979811,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9282f1d881/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-24.594687.json,1791389485.977891,1 +v1annealC_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.19885358563158426,0.00594219052542017,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9282f1d881/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-24.594687.json,1791389485.977891,1 +v1annealC_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.1110656665699,0.013018013981765367,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9282f1d881/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-11-24.594687.json,1791389485.977891,1 +v1annealC_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.04106925992409,0.018920235347903058,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fb235d44ac/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-41.656261.json,1791390582.951081,1 +v1annealC_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6676291061127745,0.004309692635589395,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fb235d44ac/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-41.656261.json,1791390582.951081,1 +v1annealC_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22594312596833221,0.006038730989074991,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fb235d44ac/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-41.656261.json,1791390582.951081,1 +v1annealC_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.80546684361852,0.013080966084789421,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fb235d44ac/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-29-41.656261.json,1791390582.951081,1 +v1annealC_merge3_116k_120k,global_mgsm_ca,5,lm-eval,vllm,,exact_match,flexible-extract,0.26,0.0277973157526443,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/602b6524cb_2026-10-07T16-15-36.256892.json,1791389568.7688653,1 +v1annealC_merge3_116k_120k,global_mgsm_cs,5,lm-eval,vllm,,exact_match,flexible-extract,0.272,0.028200088296309996,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9e4ee0be10_2026-10-07T16-05-28.099094.json,1791388956.2650921,1 +v1annealC_merge3_116k_120k,global_mgsm_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.264,0.027934518957690908,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bbcb79e63_2026-10-07T15-53-11.832964.json,1791388218.3493915,1 +v1annealC_merge3_116k_120k,global_mgsm_el,5,lm-eval,vllm,,exact_match,flexible-extract,0.328,0.029752391824475383,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3c4ad96b63_2026-10-07T15-51-08.960679.json,1791388089.7980793,1 +v1annealC_merge3_116k_120k,global_mgsm_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.288,0.02869700458739821,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c88c19f489_2026-10-07T16-03-13.615492.json,1791388830.5415084,1 +v1annealC_merge3_116k_120k,global_mgsm_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.288,0.02869700458739821,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/587d822091_2026-10-07T16-01-11.220436.json,1791388701.9476569,1 +v1annealC_merge3_116k_120k,global_mgsm_eu,5,lm-eval,vllm,,exact_match,flexible-extract,0.236,0.026909337594953845,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/76db918ff7_2026-10-07T16-05-39.182414.json,1791388953.2364497,1 +v1annealC_merge3_116k_120k,global_mgsm_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.288,0.02869700458739821,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/250440f09a_2026-10-07T15-47-04.137501.json,1791387859.342718,1 +v1annealC_merge3_116k_120k,global_mgsm_gl,5,lm-eval,vllm,,exact_match,flexible-extract,0.264,0.027934518957690908,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a815c9cd9_2026-10-07T15-48-50.968184.json,1791387962.1236925,1 +v1annealC_merge3_116k_120k,global_mgsm_hu,5,lm-eval,vllm,,exact_match,flexible-extract,0.264,0.027934518957690908,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0050da8532_2026-10-07T16-27-38.412047.json,1791390290.8224137,1 +v1annealC_merge3_116k_120k,global_mgsm_sr,5,lm-eval,vllm,,exact_match,flexible-extract,0.304,0.029150213374159673,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fa61a34c92_2026-10-07T16-15-30.707273.json,1791389564.956766,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs,5,lm-eval,vllm,yes,acc,none,0.639225181598063,0.0038419570502361594,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_abstract_algebra,5,lm-eval,vllm,,acc,none,0.32,0.04688261722621507,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_anatomy,5,lm-eval,vllm,,acc,none,0.5777777777777777,0.042667634040995855,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_astronomy,5,lm-eval,vllm,,acc,none,0.7236842105263158,0.03639057569952929,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_business_ethics,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6679245283018868,0.028985455652334374,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_college_chemistry,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_college_computer_science,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_college_physics,5,lm-eval,vllm,,acc,none,0.4215686274509804,0.04913595201274502,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_computer_security,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_conceptual_physics,5,lm-eval,vllm,,acc,none,0.723404255319149,0.0292418838696288,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6275862068965518,0.0402873153294756,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4523809523809524,0.025634258115554927,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_formal_logic,5,lm-eval,vllm,,acc,none,0.42857142857142855,0.04426266681379905,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_global_facts,5,lm-eval,vllm,,acc,none,0.34,0.04760952285695233,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_biology,5,lm-eval,vllm,,acc,none,0.8129032258064516,0.02218571009225229,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5615763546798029,0.034912078574865175,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_european_history,5,lm-eval,vllm,,acc,none,0.793939393939394,0.03158415324047706,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_geography,5,lm-eval,vllm,,acc,none,0.8282828282828283,0.02686971618742987,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8808290155440415,0.02338193534812143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7153846153846154,0.022878322799706304,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.337037037037037,0.028820884666253255,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8067226890756303,0.02564947026588922,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_physics,5,lm-eval,vllm,,acc,none,0.4768211920529801,0.04078093859163086,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8201834862385321,0.016465345467391534,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6064814814814815,0.033317478763703126,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7941176470588235,0.028379449451588684,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8227848101265823,0.024856364184503203,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_human_aging,5,lm-eval,vllm,,acc,none,0.7443946188340808,0.029275891003969906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_human_sexuality,5,lm-eval,vllm,,acc,none,0.7862595419847328,0.03595461611774691,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_humanities,5,lm-eval,vllm,yes,acc,none,0.58384697130712,0.0068153781909821316,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_jurisprudence,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.04330043749650743,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7116564417177914,0.03559039531617345,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_machine_learning,5,lm-eval,vllm,,acc,none,0.45535714285714285,0.04726835553719097,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_management,5,lm-eval,vllm,,acc,none,0.7281553398058253,0.04405268024140923,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_medical_genetics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_miscellaneous,5,lm-eval,vllm,,acc,none,0.7432950191570882,0.01562048026306451,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_moral_disputes,5,lm-eval,vllm,,acc,none,0.708092485549133,0.02447699407624737,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_moral_scenarios,5,lm-eval,vllm,,acc,none,0.394413407821229,0.016345386762104078,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_nutrition,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.024630048979824716,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_other,5,lm-eval,vllm,yes,acc,none,0.6729964596073382,0.00813331878792918,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_philosophy,5,lm-eval,vllm,,acc,none,0.6881028938906752,0.026311858071854183,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_prehistory,5,lm-eval,vllm,,acc,none,0.7469135802469136,0.02419180860071302,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_professional_accounting,5,lm-eval,vllm,,acc,none,0.425531914893617,0.02949482760014435,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_professional_law,5,lm-eval,vllm,,acc,none,0.47392438070404175,0.012752858346533136,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_professional_medicine,5,lm-eval,vllm,,acc,none,0.6507352941176471,0.02895975519682485,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_professional_psychology,5,lm-eval,vllm,,acc,none,0.6437908496732027,0.01937333242072444,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_security_studies,5,lm-eval,vllm,,acc,none,0.7877551020408163,0.026176967197866795,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7543061423464413,0.007592753742741412,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_stem,5,lm-eval,vllm,yes,acc,none,0.5762765620044402,0.008378267757282048,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_cs_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc7dec4900_2026-10-07T15-49-40.130120.json,1791387852.1729085,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de,5,lm-eval,vllm,yes,acc,none,0.6306793904002279,0.0038501777387753493,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_abstract_algebra,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_astronomy,5,lm-eval,vllm,,acc,none,0.7171052631578947,0.03665349695640767,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6452830188679245,0.029445175328199655,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_college_medicine,5,lm-eval,vllm,,acc,none,0.6763005780346821,0.03567603799639168,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_college_physics,5,lm-eval,vllm,,acc,none,0.4019607843137255,0.04878608714466993,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_computer_security,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6808510638297872,0.03047297336338012,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6344827586206897,0.04013124195424389,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4365079365079365,0.025542846817400516,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_formal_logic,5,lm-eval,vllm,,acc,none,0.49206349206349204,0.04471572536294351,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_biology,5,lm-eval,vllm,,acc,none,0.8225806451612904,0.021732540689329255,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5911330049261084,0.034590588158832314,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_geography,5,lm-eval,vllm,,acc,none,0.8282828282828283,0.02686971618742987,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7025641025641025,0.02317740813146596,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.32592592592592595,0.028578348365473138,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8109243697478992,0.025435119438105305,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8256880733944955,0.01626567563201035,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5324074074074074,0.03402801581358966,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7990196078431373,0.02812597226565433,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_high_school_world_history,5,lm-eval,vllm,,acc,none,0.810126582278481,0.025530100460233456,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_human_aging,5,lm-eval,vllm,,acc,none,0.672645739910314,0.0314938467099413,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_human_sexuality,5,lm-eval,vllm,,acc,none,0.732824427480916,0.03880848301082397,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_humanities,5,lm-eval,vllm,yes,acc,none,0.5674814027630181,0.0067930633169641765,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_international_law,5,lm-eval,vllm,,acc,none,0.7851239669421488,0.037494924487096966,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_jurisprudence,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.04330043749650743,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7239263803680982,0.035123852837050454,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_machine_learning,5,lm-eval,vllm,,acc,none,0.4017857142857143,0.04653333146973646,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_management,5,lm-eval,vllm,,acc,none,0.7184466019417476,0.044532548363264673,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_marketing,5,lm-eval,vllm,,acc,none,0.8504273504273504,0.023365051491753757,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_medical_genetics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_miscellaneous,5,lm-eval,vllm,,acc,none,0.768837803320562,0.015075523238101072,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_moral_disputes,5,lm-eval,vllm,,acc,none,0.6676300578034682,0.025361168749688214,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3407821229050279,0.015852002449862183,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_other,5,lm-eval,vllm,yes,acc,none,0.6694560669456067,0.008176941371560878,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_philosophy,5,lm-eval,vllm,,acc,none,0.7138263665594855,0.02567025924218898,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_prehistory,5,lm-eval,vllm,,acc,none,0.7098765432098766,0.025251173936494977,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_professional_accounting,5,lm-eval,vllm,,acc,none,0.4326241134751773,0.029555454236778834,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_professional_law,5,lm-eval,vllm,,acc,none,0.4602346805736636,0.012729785386598602,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_professional_medicine,5,lm-eval,vllm,,acc,none,0.5955882352941176,0.029812630701569736,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_professional_psychology,5,lm-eval,vllm,,acc,none,0.6617647058823529,0.019139943748487008,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_security_studies,5,lm-eval,vllm,,acc,none,0.7510204081632653,0.027682979522960276,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_social_sciences,5,lm-eval,vllm,yes,acc,none,0.750731231719207,0.007644105412380844,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_stem,5,lm-eval,vllm,yes,acc,none,0.569616238503013,0.008407825621402534,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_de_world_religions,5,lm-eval,vllm,,acc,none,0.783625730994152,0.03158149539338735,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/990c167b0f_2026-10-07T16-04-10.436347.json,1791388705.5566435,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el,5,lm-eval,vllm,yes,acc,none,0.6106679960119641,0.003902586491365847,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_abstract_algebra,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_anatomy,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.042446332383532265,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_astronomy,5,lm-eval,vllm,,acc,none,0.6907894736842105,0.037610708698674764,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6377358490566037,0.029582245128384355,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_college_biology,5,lm-eval,vllm,,acc,none,0.7083333333333334,0.03800968060554863,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_college_chemistry,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_college_computer_science,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_college_medicine,5,lm-eval,vllm,,acc,none,0.6763005780346821,0.03567603799639168,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_college_physics,5,lm-eval,vllm,,acc,none,0.45098039215686275,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_computer_security,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6936170212765957,0.03013590647851759,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_econometrics,5,lm-eval,vllm,,acc,none,0.43859649122807015,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_electrical_engineering,5,lm-eval,vllm,,acc,none,0.593103448275862,0.040937939812662354,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4444444444444444,0.02559185776138215,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_formal_logic,5,lm-eval,vllm,,acc,none,0.4603174603174603,0.04458029125470974,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_global_facts,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_biology,5,lm-eval,vllm,,acc,none,0.7967741935483871,0.022891687984554897,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5566502463054187,0.03495334582162933,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7515151515151515,0.03374402644139407,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_geography,5,lm-eval,vllm,,acc,none,0.7828282828282829,0.02937661648494561,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7307692307692307,0.022489389793654804,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.34814814814814815,0.02904560029061618,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7689075630252101,0.027381406927868907,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_physics,5,lm-eval,vllm,,acc,none,0.44370860927152317,0.04056527902281736,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_psychology,5,lm-eval,vllm,,acc,none,0.7834862385321101,0.017658710594443204,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.03350991604696042,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7696078431372549,0.029554292605695046,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8185654008438819,0.025085961144579647,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_human_aging,5,lm-eval,vllm,,acc,none,0.6591928251121076,0.03181149747055356,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_human_sexuality,5,lm-eval,vllm,,acc,none,0.6717557251908397,0.041184385658063025,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_humanities,5,lm-eval,vllm,yes,acc,none,0.5432518597236982,0.006782331401606127,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_jurisprudence,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.0437331304091476,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6625766871165644,0.03714908409935573,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_machine_learning,5,lm-eval,vllm,,acc,none,0.39285714285714285,0.04635550135609972,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_management,5,lm-eval,vllm,,acc,none,0.7378640776699029,0.04354631077260595,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_marketing,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.02441494730454365,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_medical_genetics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_miscellaneous,5,lm-eval,vllm,,acc,none,0.6807151979565773,0.016671261749538653,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_moral_disputes,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.024946792225272324,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_moral_scenarios,5,lm-eval,vllm,,acc,none,0.2737430167597765,0.014912413096372446,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_nutrition,5,lm-eval,vllm,,acc,none,0.6830065359477124,0.02664327847450882,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_other,5,lm-eval,vllm,yes,acc,none,0.6446733183134857,0.00843201164567855,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_philosophy,5,lm-eval,vllm,,acc,none,0.7138263665594855,0.02567025924218898,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_prehistory,5,lm-eval,vllm,,acc,none,0.654320987654321,0.02646248777700184,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_professional_accounting,5,lm-eval,vllm,,acc,none,0.46099290780141844,0.029736592526424455,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_professional_law,5,lm-eval,vllm,,acc,none,0.45697522816166886,0.012722869501611224,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_professional_medicine,5,lm-eval,vllm,,acc,none,0.6176470588235294,0.029520095697687675,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_professional_psychology,5,lm-eval,vllm,,acc,none,0.6241830065359477,0.019594021136577423,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_social_sciences,5,lm-eval,vllm,yes,acc,none,0.731556711082223,0.007822796120332216,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_sociology,5,lm-eval,vllm,,acc,none,0.8308457711442786,0.026508590656233278,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_stem,5,lm-eval,vllm,yes,acc,none,0.5597843323818585,0.008504857780922826,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_el_world_religions,5,lm-eval,vllm,,acc,none,0.7192982456140351,0.03446296217088429,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d9e15e680_2026-10-07T15-54-45.746388.json,1791388090.815014,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en,5,lm-eval,vllm,yes,acc,none,0.6680672268907563,0.0037618363873883173,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_abstract_algebra,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_anatomy,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.042446332383532265,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_astronomy,5,lm-eval,vllm,,acc,none,0.7302631578947368,0.036117805602848975,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7094339622641509,0.027943219989337183,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_college_biology,5,lm-eval,vllm,,acc,none,0.8263888888888888,0.03167473383795719,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_college_mathematics,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_college_medicine,5,lm-eval,vllm,,acc,none,0.6705202312138728,0.03583901754736415,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_computer_security,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7319148936170212,0.028957342788342354,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_econometrics,5,lm-eval,vllm,,acc,none,0.5526315789473685,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6689655172413793,0.03921545312467122,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4603174603174603,0.025670080636909207,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_formal_logic,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.043603148600774626,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_biology,5,lm-eval,vllm,,acc,none,0.8451612903225807,0.020579287326583217,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.034139638059062394,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7878787878787878,0.031922715695482946,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_geography,5,lm-eval,vllm,,acc,none,0.8535353535353535,0.025190921114603887,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9222797927461139,0.01932180555722318,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7461538461538462,0.022066054378726312,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.3814814814814815,0.029616718927497565,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.819327731092437,0.02499196496660074,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8587155963302753,0.014933868987028072,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6435185185185185,0.03266478331527272,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.02675640153807894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8227848101265823,0.024856364184503203,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_human_aging,5,lm-eval,vllm,,acc,none,0.7488789237668162,0.029105220833224605,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_humanities,5,lm-eval,vllm,yes,acc,none,0.6114771519659936,0.006731318398659917,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_international_law,5,lm-eval,vllm,,acc,none,0.859504132231405,0.03172233426002156,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_jurisprudence,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.040774947092526284,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7668711656441718,0.03322015795776743,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_machine_learning,5,lm-eval,vllm,,acc,none,0.4375,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_marketing,5,lm-eval,vllm,,acc,none,0.9102564102564102,0.018724301741941646,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_miscellaneous,5,lm-eval,vllm,,acc,none,0.7994891443167306,0.01431765370859427,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_moral_scenarios,5,lm-eval,vllm,,acc,none,0.40670391061452515,0.016428811915898962,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_nutrition,5,lm-eval,vllm,,acc,none,0.738562091503268,0.025160998214292445,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_other,5,lm-eval,vllm,yes,acc,none,0.7064692629546186,0.00789593408136539,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_philosophy,5,lm-eval,vllm,,acc,none,0.729903536977492,0.02521804037341055,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_prehistory,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.02346842983245111,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_professional_accounting,5,lm-eval,vllm,,acc,none,0.49645390070921985,0.029826749153280853,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_professional_law,5,lm-eval,vllm,,acc,none,0.500651890482399,0.012770225252255563,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_professional_medicine,5,lm-eval,vllm,,acc,none,0.6470588235294118,0.02902942281568144,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_professional_psychology,5,lm-eval,vllm,,acc,none,0.6993464052287581,0.01855063450295291,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_security_studies,5,lm-eval,vllm,,acc,none,0.746938775510204,0.027833023871399704,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_social_sciences,5,lm-eval,vllm,yes,acc,none,0.783230419239519,0.007284331541663263,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_stem,5,lm-eval,vllm,yes,acc,none,0.6022835394862036,0.008289339169115364,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_en_world_religions,5,lm-eval,vllm,,acc,none,0.7719298245614035,0.03218093795602355,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/657b26450d_2026-10-07T15-53-48.044077.json,1791388091.767676,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es,5,lm-eval,vllm,yes,acc,none,0.6358780800455776,0.0038363043605687108,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_abstract_algebra,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_anatomy,5,lm-eval,vllm,,acc,none,0.5259259259259259,0.043135316967505756,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_astronomy,5,lm-eval,vllm,,acc,none,0.7368421052631579,0.03583496176361067,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6490566037735849,0.029373646253234693,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_college_biology,5,lm-eval,vllm,,acc,none,0.75,0.03621034121889507,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_college_computer_science,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_college_mathematics,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_college_medicine,5,lm-eval,vllm,,acc,none,0.6647398843930635,0.03599586301247073,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_college_physics,5,lm-eval,vllm,,acc,none,0.4019607843137255,0.04878608714466993,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_computer_security,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6893617021276596,0.03025123757921315,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6413793103448275,0.03996629574876715,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.455026455026455,0.025646928361049343,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_formal_logic,5,lm-eval,vllm,,acc,none,0.5079365079365079,0.04471572536294351,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_biology,5,lm-eval,vllm,,acc,none,0.8258064516129032,0.02157624818451461,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5911330049261084,0.034590588158832314,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_geography,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.02747960301053882,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7333333333333333,0.022421273612923794,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.337037037037037,0.028820884666253255,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7605042016806722,0.02772206549336123,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8348623853211009,0.015919557829976096,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6157407407407407,0.03317354514310747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8284313725490197,0.026460569561240675,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_high_school_world_history,5,lm-eval,vllm,,acc,none,0.810126582278481,0.025530100460233456,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_human_aging,5,lm-eval,vllm,,acc,none,0.6995515695067265,0.030769352008229164,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_humanities,5,lm-eval,vllm,yes,acc,none,0.5706695005313497,0.006724126269914769,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_international_law,5,lm-eval,vllm,,acc,none,0.7933884297520661,0.03695980128098826,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_jurisprudence,5,lm-eval,vllm,,acc,none,0.7407407407407407,0.04236511258094632,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7116564417177914,0.03559039531617345,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_machine_learning,5,lm-eval,vllm,,acc,none,0.42857142857142855,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_management,5,lm-eval,vllm,,acc,none,0.7766990291262136,0.041235531898914324,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_miscellaneous,5,lm-eval,vllm,,acc,none,0.7535121328224776,0.015411308769686863,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_moral_disputes,5,lm-eval,vllm,,acc,none,0.7023121387283237,0.024617055388677027,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3128491620111732,0.015506892594647189,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_nutrition,5,lm-eval,vllm,,acc,none,0.7156862745098039,0.025829163272757385,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_other,5,lm-eval,vllm,yes,acc,none,0.6826520759575153,0.00816204596711199,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_philosophy,5,lm-eval,vllm,,acc,none,0.7459807073954984,0.024723861504771655,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_prehistory,5,lm-eval,vllm,,acc,none,0.691358024691358,0.025702640260603798,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_professional_accounting,5,lm-eval,vllm,,acc,none,0.4858156028368794,0.029815494483682023,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_professional_law,5,lm-eval,vllm,,acc,none,0.4680573663624511,0.012744149704869631,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_professional_medicine,5,lm-eval,vllm,,acc,none,0.6691176470588235,0.028582709753898396,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_professional_psychology,5,lm-eval,vllm,,acc,none,0.6683006535947712,0.019047485239360454,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_public_relations,5,lm-eval,vllm,,acc,none,0.6090909090909091,0.046737523336702363,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_security_studies,5,lm-eval,vllm,,acc,none,0.746938775510204,0.027833023871399704,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7491062723431914,0.007676265367982093,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_sociology,5,lm-eval,vllm,,acc,none,0.7711442786069652,0.0297052840567725,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_stem,5,lm-eval,vllm,yes,acc,none,0.576593720266413,0.00839169824293487,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_virology,5,lm-eval,vllm,,acc,none,0.5421686746987951,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_es_world_religions,5,lm-eval,vllm,,acc,none,0.8070175438596491,0.030267457554898448,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/162d9fdac2_2026-10-07T16-06-16.906470.json,1791388833.5855577,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr,5,lm-eval,vllm,yes,acc,none,0.6289702321606608,0.003855132280905116,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_anatomy,5,lm-eval,vllm,,acc,none,0.5481481481481482,0.04299268905480864,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_astronomy,5,lm-eval,vllm,,acc,none,0.6973684210526315,0.03738520676119667,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_business_ethics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6716981132075471,0.028901593612411777,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_college_biology,5,lm-eval,vllm,,acc,none,0.7569444444444444,0.03586879280080337,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_college_computer_science,5,lm-eval,vllm,,acc,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_college_mathematics,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_college_medicine,5,lm-eval,vllm,,acc,none,0.6763005780346821,0.03567603799639168,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6893617021276596,0.03025123757921315,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_econometrics,5,lm-eval,vllm,,acc,none,0.43859649122807015,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.5862068965517241,0.04104269211806236,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.46296296296296297,0.025680564640056906,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_formal_logic,5,lm-eval,vllm,,acc,none,0.4444444444444444,0.044444444444444446,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_global_facts,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8096774193548387,0.02233170761182313,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5763546798029556,0.03476725747649036,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8363636363636363,0.028887872395487978,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8131313131313131,0.02777253333421894,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6846153846153846,0.023559646983189894,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.35555555555555557,0.029185714949857472,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7815126050420168,0.026841514322958934,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_physics,5,lm-eval,vllm,,acc,none,0.4966887417218543,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8165137614678899,0.016595259710399303,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.03350991604696042,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7745098039215687,0.029331162294251714,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.810126582278481,0.025530100460233456,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_human_aging,5,lm-eval,vllm,,acc,none,0.7130044843049327,0.030360379710291947,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_human_sexuality,5,lm-eval,vllm,,acc,none,0.732824427480916,0.03880848301082397,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_humanities,5,lm-eval,vllm,yes,acc,none,0.5685441020191286,0.006717307079910021,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_international_law,5,lm-eval,vllm,,acc,none,0.8677685950413223,0.030922788320445795,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7592592592592593,0.041331194402438355,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7055214723926381,0.03581165790474083,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_machine_learning,5,lm-eval,vllm,,acc,none,0.42857142857142855,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_medical_genetics,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7279693486590039,0.01591336744750049,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7196531791907514,0.024182427496577626,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3340782122905028,0.015774911422381653,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_nutrition,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.024848018263875137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_other,5,lm-eval,vllm,yes,acc,none,0.6729964596073382,0.008200616600916023,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_philosophy,5,lm-eval,vllm,,acc,none,0.7266881028938906,0.025311765975426094,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_prehistory,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.025171041915309698,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_professional_accounting,5,lm-eval,vllm,,acc,none,0.46808510638297873,0.02976667507587383,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_professional_law,5,lm-eval,vllm,,acc,none,0.4471968709256845,0.0126988252524352,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6727941176470589,0.028501452860396626,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6356209150326797,0.0194695182215738,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7361065973350667,0.007768489518517975,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_sociology,5,lm-eval,vllm,,acc,none,0.8109452736318408,0.02768691358801299,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_stem,5,lm-eval,vllm,yes,acc,none,0.5712020298128766,0.008457533601568494,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_fr_world_religions,5,lm-eval,vllm,,acc,none,0.8070175438596491,0.030267457554898448,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ead7d3232_2026-10-07T16-08-23.764033.json,1791388946.0012717,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it,5,lm-eval,vllm,yes,acc,none,0.6397236860846033,0.003838739108810309,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_abstract_algebra,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_anatomy,5,lm-eval,vllm,,acc,none,0.5407407407407407,0.04304979692464244,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_astronomy,5,lm-eval,vllm,,acc,none,0.7236842105263158,0.03639057569952929,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6792452830188679,0.02872750295788032,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_college_biology,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03476590104304133,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_college_computer_science,5,lm-eval,vllm,,acc,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_college_mathematics,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_college_medicine,5,lm-eval,vllm,,acc,none,0.6358381502890174,0.03669072477416912,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_college_physics,5,lm-eval,vllm,,acc,none,0.39215686274509803,0.04858083574266346,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_computer_security,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7063829787234043,0.02977164271249127,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_econometrics,5,lm-eval,vllm,,acc,none,0.5263157894736842,0.04697085136647865,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6620689655172414,0.03941707632064884,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4312169312169312,0.025506481698138284,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_formal_logic,5,lm-eval,vllm,,acc,none,0.5079365079365079,0.04471572536294351,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.03481904844438804,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7878787878787878,0.031922715695482946,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8911917098445595,0.02247325333276875,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7153846153846154,0.022878322799706304,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.35185185185185186,0.02911661760608302,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7857142857142857,0.026653531596715505,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_physics,5,lm-eval,vllm,,acc,none,0.48344370860927155,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8220183486238533,0.016399436366612896,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6157407407407407,0.03317354514310747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7892156862745098,0.028626547912437423,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7974683544303798,0.02616056824660147,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_human_aging,5,lm-eval,vllm,,acc,none,0.7040358744394619,0.03063659134869978,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_humanities,5,lm-eval,vllm,yes,acc,none,0.5783209351753453,0.00681364983236172,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_jurisprudence,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.0437331304091476,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7055214723926381,0.03581165790474083,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_machine_learning,5,lm-eval,vllm,,acc,none,0.41964285714285715,0.04684099321077107,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_management,5,lm-eval,vllm,,acc,none,0.7378640776699029,0.04354631077260595,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_marketing,5,lm-eval,vllm,,acc,none,0.8376068376068376,0.024161618127987734,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_miscellaneous,5,lm-eval,vllm,,acc,none,0.7598978288633461,0.01527468521373415,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_moral_disputes,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.024105712607754307,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_moral_scenarios,5,lm-eval,vllm,,acc,none,0.37094972067039106,0.01615591072134164,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_nutrition,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.025261691219729484,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_other,5,lm-eval,vllm,yes,acc,none,0.6726746057289991,0.008191814356739673,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_philosophy,5,lm-eval,vllm,,acc,none,0.7138263665594855,0.02567025924218898,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_prehistory,5,lm-eval,vllm,,acc,none,0.7191358024691358,0.025006469755799246,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_professional_accounting,5,lm-eval,vllm,,acc,none,0.4716312056737589,0.029779450957303062,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_professional_law,5,lm-eval,vllm,,acc,none,0.4680573663624511,0.012744149704869631,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_professional_medicine,5,lm-eval,vllm,,acc,none,0.6066176470588235,0.029674288281311183,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_professional_psychology,5,lm-eval,vllm,,acc,none,0.6797385620915033,0.018875682938069425,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_security_studies,5,lm-eval,vllm,,acc,none,0.7959183673469388,0.02580128347509046,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_social_sciences,5,lm-eval,vllm,yes,acc,none,0.764380890477738,0.007514426629025973,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_sociology,5,lm-eval,vllm,,acc,none,0.845771144278607,0.025538433368578303,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_stem,5,lm-eval,vllm,yes,acc,none,0.5772280367903584,0.008364039577146466,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_it_world_religions,5,lm-eval,vllm,,acc,none,0.7602339181286549,0.03274485211946959,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98afa4e849_2026-10-07T16-06-12.246084.json,1791388832.5224726,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt,5,lm-eval,vllm,yes,acc,none,0.616009115510611,0.0038906817196076395,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.31,0.04648231987117317,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_anatomy,5,lm-eval,vllm,,acc,none,0.6222222222222222,0.041883075375958506,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_astronomy,5,lm-eval,vllm,,acc,none,0.75,0.03523807393012047,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_business_ethics,5,lm-eval,vllm,,acc,none,0.57,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6792452830188679,0.02872750295788032,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_college_biology,5,lm-eval,vllm,,acc,none,0.7361111111111112,0.036856510958975304,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_college_medicine,5,lm-eval,vllm,,acc,none,0.6069364161849711,0.0372424959581773,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_college_physics,5,lm-eval,vllm,,acc,none,0.3627450980392157,0.047840607041056527,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_computer_security,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6851063829787234,0.030363582197238136,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_econometrics,5,lm-eval,vllm,,acc,none,0.47368421052631576,0.046970851366478654,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.593103448275862,0.040937939812662354,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.42592592592592593,0.02546714904546955,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_formal_logic,5,lm-eval,vllm,,acc,none,0.48412698412698413,0.044698818540726104,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_global_facts,5,lm-eval,vllm,,acc,none,0.32,0.04688261722621507,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8096774193548387,0.02233170761182313,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.4876847290640394,0.035169204442208966,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7636363636363637,0.03317505930009174,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_geography,5,lm-eval,vllm,,acc,none,0.7929292929292929,0.02886977846026699,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8601036269430051,0.025033870583015143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.676923076923077,0.023710888501970607,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.35555555555555557,0.029185714949857472,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7815126050420168,0.026841514322958934,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_physics,5,lm-eval,vllm,,acc,none,0.5165562913907285,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.7871559633027523,0.01754937638931373,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.03350991604696042,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.030964517926923372,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7805907172995781,0.026939106581553945,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_human_aging,5,lm-eval,vllm,,acc,none,0.695067264573991,0.03089861088247754,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_humanities,5,lm-eval,vllm,yes,acc,none,0.554941551540914,0.006808666280284368,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_jurisprudence,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.0448993107359131,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6625766871165644,0.03714908409935573,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_machine_learning,5,lm-eval,vllm,,acc,none,0.42857142857142855,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_marketing,5,lm-eval,vllm,,acc,none,0.8376068376068376,0.024161618127987734,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_medical_genetics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_miscellaneous,5,lm-eval,vllm,,acc,none,0.6845466155810983,0.016617501738763366,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.024257901705323326,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3016759776536313,0.015350767572220217,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_nutrition,5,lm-eval,vllm,,acc,none,0.7124183006535948,0.025917806117147137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_other,5,lm-eval,vllm,yes,acc,none,0.6420984872867718,0.008354162340915688,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_prehistory,5,lm-eval,vllm,,acc,none,0.7098765432098766,0.025251173936494977,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_professional_accounting,5,lm-eval,vllm,,acc,none,0.41134751773049644,0.02935491115994096,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_professional_law,5,lm-eval,vllm,,acc,none,0.4641460234680574,0.012737361318730512,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6213235294117647,0.02946513363977605,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_professional_psychology,5,lm-eval,vllm,,acc,none,0.6503267973856209,0.019291961895066337,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_security_studies,5,lm-eval,vllm,,acc,none,0.7346938775510204,0.028263889943784655,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.734481637959051,0.007823360927978437,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_stem,5,lm-eval,vllm,yes,acc,none,0.5658103393593403,0.008423305423752086,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_virology,5,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_lt_world_religions,5,lm-eval,vllm,,acc,none,0.7368421052631579,0.033773102522091994,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8944bc217_2026-10-07T15-41-28.360152.json,1791387347.3621118,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl,5,lm-eval,vllm,yes,acc,none,0.6353083606323886,0.0038406730394622375,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_anatomy,5,lm-eval,vllm,,acc,none,0.5851851851851851,0.04256193767901412,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_astronomy,5,lm-eval,vllm,,acc,none,0.7171052631578947,0.03665349695640767,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_business_ethics,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_college_chemistry,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_college_mathematics,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_college_physics,5,lm-eval,vllm,,acc,none,0.47058823529411764,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7063829787234043,0.02977164271249127,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6344827586206897,0.04013124195424389,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4444444444444444,0.02559185776138215,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_formal_logic,5,lm-eval,vllm,,acc,none,0.4523809523809524,0.04451807959055331,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8387096774193549,0.020923327006423326,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.03481904844438804,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7818181818181819,0.032250781083062896,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8080808080808081,0.028057791672989062,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7153846153846154,0.022878322799706304,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.35555555555555557,0.029185714949857472,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7563025210084033,0.027886828078380516,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8311926605504587,0.016060056268530364,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.03293377139415187,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7843137254901961,0.028867431449849337,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8227848101265823,0.024856364184503203,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_human_aging,5,lm-eval,vllm,,acc,none,0.6771300448430493,0.031381476375754995,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7175572519083969,0.039484061257683584,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_humanities,5,lm-eval,vllm,yes,acc,none,0.5749202975557917,0.0067425411976694246,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.038935425188248496,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7361963190184049,0.03462419931615622,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_machine_learning,5,lm-eval,vllm,,acc,none,0.39285714285714285,0.04635550135609972,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_management,5,lm-eval,vllm,,acc,none,0.8058252427184466,0.03916667762822582,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_medical_genetics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7177522349936143,0.01609530296987855,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3474860335195531,0.015925564060208213,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_nutrition,5,lm-eval,vllm,,acc,none,0.7418300653594772,0.025058503316958167,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_other,5,lm-eval,vllm,yes,acc,none,0.668490505310589,0.008226055597118217,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_philosophy,5,lm-eval,vllm,,acc,none,0.7331189710610932,0.0251226376088166,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_prehistory,5,lm-eval,vllm,,acc,none,0.7067901234567902,0.02532988817190095,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_professional_accounting,5,lm-eval,vllm,,acc,none,0.46099290780141844,0.029736592526424455,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_professional_law,5,lm-eval,vllm,,acc,none,0.45827900912646674,0.012725701656953702,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6397058823529411,0.02916312857067069,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.019070985589687436,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_public_relations,5,lm-eval,vllm,,acc,none,0.6272727272727273,0.04631381319425461,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7500812479688008,0.00765011870269444,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_sociology,5,lm-eval,vllm,,acc,none,0.8308457711442786,0.026508590656233278,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_stem,5,lm-eval,vllm,yes,acc,none,0.5807167776720583,0.00836032648941637,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_nl_world_religions,5,lm-eval,vllm,,acc,none,0.7602339181286549,0.03274485211946959,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03e4ee5b56_2026-10-07T16-10-19.777546.json,1791389072.4333184,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl,5,lm-eval,vllm,yes,acc,none,0.6266201395812563,0.003850974085482242,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_anatomy,5,lm-eval,vllm,,acc,none,0.4962962962962963,0.043192236258113345,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_astronomy,5,lm-eval,vllm,,acc,none,0.6973684210526315,0.03738520676119667,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_business_ethics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_college_biology,5,lm-eval,vllm,,acc,none,0.7152777777777778,0.037738099906869334,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_college_chemistry,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_college_computer_science,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_college_mathematics,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_college_medicine,5,lm-eval,vllm,,acc,none,0.6647398843930635,0.03599586301247073,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_college_physics,5,lm-eval,vllm,,acc,none,0.43137254901960786,0.049280995972875316,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_computer_security,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7063829787234043,0.02977164271249127,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_econometrics,5,lm-eval,vllm,,acc,none,0.47368421052631576,0.046970851366478654,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6137931034482759,0.04057324734419032,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4365079365079365,0.025542846817400516,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_formal_logic,5,lm-eval,vllm,,acc,none,0.48412698412698413,0.044698818540726104,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_global_facts,5,lm-eval,vllm,,acc,none,0.35,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8290322580645161,0.021417242936321575,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5911330049261084,0.034590588158832314,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_geography,5,lm-eval,vllm,,acc,none,0.7878787878787878,0.029126522834586777,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8497409326424871,0.025787723180723855,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6974358974358974,0.02329088805377271,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.34444444444444444,0.02897264888484431,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7563025210084033,0.027886828078380516,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_physics,5,lm-eval,vllm,,acc,none,0.4900662251655629,0.040816771072484305,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8220183486238533,0.016399436366612896,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5648148148148148,0.033812000056435254,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7794117647058824,0.029102254389674065,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8143459915611815,0.025310495376944835,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_human_aging,5,lm-eval,vllm,,acc,none,0.695067264573991,0.03089861088247754,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7099236641221374,0.03980066246467765,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_humanities,5,lm-eval,vllm,yes,acc,none,0.5636556854410202,0.006724546476797196,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_international_law,5,lm-eval,vllm,,acc,none,0.859504132231405,0.03172233426002156,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_machine_learning,5,lm-eval,vllm,,acc,none,0.44642857142857145,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_management,5,lm-eval,vllm,,acc,none,0.7378640776699029,0.04354631077260595,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_medical_genetics,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7369093231162197,0.015745497169049005,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.02454761779480379,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.2905027932960894,0.015183844307206257,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_other,5,lm-eval,vllm,yes,acc,none,0.6681686514322498,0.008170059549660151,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_prehistory,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.026041766202717188,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_professional_accounting,5,lm-eval,vllm,,acc,none,0.425531914893617,0.02949482760014435,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_professional_law,5,lm-eval,vllm,,acc,none,0.47327249022164275,0.012751977967675987,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6580882352941176,0.02881472242225415,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6617647058823529,0.019139943748487008,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7409814754631134,0.007767962579274352,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_sociology,5,lm-eval,vllm,,acc,none,0.7960199004975125,0.02849317624532607,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_stem,5,lm-eval,vllm,yes,acc,none,0.5680304471931494,0.008436239206287189,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_virology,5,lm-eval,vllm,,acc,none,0.4819277108433735,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pl_world_religions,5,lm-eval,vllm,,acc,none,0.7719298245614035,0.03218093795602355,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60515bccb7_2026-10-07T15-51-45.557253.json,1791387968.3035243,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt,5,lm-eval,vllm,yes,acc,none,0.6341689218060106,0.003814253930895868,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.34,0.04760952285695233,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_anatomy,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.042446332383532265,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_astronomy,5,lm-eval,vllm,,acc,none,0.75,0.03523807393012047,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6754716981132075,0.02881561571343209,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_college_biology,5,lm-eval,vllm,,acc,none,0.7430555555555556,0.03653946969442102,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_college_mathematics,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_college_medicine,5,lm-eval,vllm,,acc,none,0.6936416184971098,0.035149425512674394,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_college_physics,5,lm-eval,vllm,,acc,none,0.4117647058823529,0.048971049527263624,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6808510638297872,0.03047297336338012,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6551724137931034,0.03960933549451213,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4021164021164021,0.02525303255499767,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_formal_logic,5,lm-eval,vllm,,acc,none,0.4603174603174603,0.04458029125470974,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_global_facts,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8290322580645161,0.021417242936321575,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.03481904844438804,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.030117688929503603,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8080808080808081,0.028057791672989062,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7307692307692307,0.022489389793654804,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.35555555555555557,0.029185714949857472,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7773109243697479,0.027025433498882392,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8385321100917431,0.01577623925616323,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.03350991604696042,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7892156862745098,0.028626547912437423,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8143459915611815,0.025310495376944835,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_human_aging,5,lm-eval,vllm,,acc,none,0.7130044843049327,0.030360379710291947,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7862595419847328,0.03595461611774691,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_humanities,5,lm-eval,vllm,yes,acc,none,0.5668437832093518,0.006665034486069424,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_international_law,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.03520893951097652,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_machine_learning,5,lm-eval,vllm,,acc,none,0.42857142857142855,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_marketing,5,lm-eval,vllm,,acc,none,0.8205128205128205,0.025140935950335442,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7394636015325671,0.015696008563807068,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7543352601156069,0.023176298203992085,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.28268156424581004,0.015060381730018045,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_nutrition,5,lm-eval,vllm,,acc,none,0.7418300653594772,0.025058503316958167,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_other,5,lm-eval,vllm,yes,acc,none,0.6765368522690698,0.008193240951928799,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_philosophy,5,lm-eval,vllm,,acc,none,0.7041800643086816,0.025922371788818833,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_prehistory,5,lm-eval,vllm,,acc,none,0.7191358024691358,0.025006469755799246,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_professional_accounting,5,lm-eval,vllm,,acc,none,0.4716312056737589,0.029779450957303062,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_professional_law,5,lm-eval,vllm,,acc,none,0.46740547588005216,0.012743072942653333,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6213235294117647,0.02946513363977605,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_professional_psychology,5,lm-eval,vllm,,acc,none,0.6748366013071896,0.01895088677080626,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_security_studies,5,lm-eval,vllm,,acc,none,0.7510204081632653,0.027682979522960276,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7598310042248944,0.007557168910613565,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_stem,5,lm-eval,vllm,yes,acc,none,0.5702505550269584,0.008370829176069112,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_pt_world_religions,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.03126781714663182,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfb730179a_2026-10-07T15-50-04.204078.json,1791387867.8676984,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro,5,lm-eval,vllm,yes,acc,none,0.6356644352656317,0.0038540208515633655,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_abstract_algebra,5,lm-eval,vllm,,acc,none,0.34,0.04760952285695233,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_astronomy,5,lm-eval,vllm,,acc,none,0.6842105263157895,0.03782728980865462,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6754716981132075,0.02881561571343209,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_college_biology,5,lm-eval,vllm,,acc,none,0.75,0.03621034121889507,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_college_computer_science,5,lm-eval,vllm,,acc,none,0.57,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_college_mathematics,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_college_medicine,5,lm-eval,vllm,,acc,none,0.6705202312138728,0.03583901754736415,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6893617021276596,0.03025123757921315,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_econometrics,5,lm-eval,vllm,,acc,none,0.4473684210526316,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6620689655172414,0.03941707632064884,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.42592592592592593,0.02546714904546955,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_formal_logic,5,lm-eval,vllm,,acc,none,0.5396825396825397,0.04458029125470974,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_global_facts,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_biology,5,lm-eval,vllm,,acc,none,0.8548387096774194,0.020039563628053293,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5960591133004927,0.03452453903822033,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_geography,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.02747960301053882,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8497409326424871,0.025787723180723855,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7051282051282052,0.023119362758232283,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.35555555555555557,0.029185714949857472,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7815126050420168,0.026841514322958934,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8201834862385321,0.016465345467391534,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6018518518518519,0.033384734032073975,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.02977177522814563,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7974683544303798,0.02616056824660147,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_human_aging,5,lm-eval,vllm,,acc,none,0.7623318385650224,0.02856807946471428,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_humanities,5,lm-eval,vllm,yes,acc,none,0.5789585547290117,0.006824067025404341,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_jurisprudence,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.04414343666854928,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7361963190184049,0.03462419931615622,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_machine_learning,5,lm-eval,vllm,,acc,none,0.4017857142857143,0.04653333146973646,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_miscellaneous,5,lm-eval,vllm,,acc,none,0.735632183908046,0.01576998484069047,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_moral_disputes,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.024405173935783293,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4,0.01638463841038081,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_nutrition,5,lm-eval,vllm,,acc,none,0.761437908496732,0.02440439492808785,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_other,5,lm-eval,vllm,yes,acc,none,0.6758931445123914,0.008136604876885377,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_philosophy,5,lm-eval,vllm,,acc,none,0.7138263665594855,0.02567025924218898,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_prehistory,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.0254071977988902,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_professional_accounting,5,lm-eval,vllm,,acc,none,0.4645390070921986,0.029752389657427127,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_professional_law,5,lm-eval,vllm,,acc,none,0.4511082138200782,0.012709037347346203,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_professional_medicine,5,lm-eval,vllm,,acc,none,0.625,0.029408372932278746,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_professional_psychology,5,lm-eval,vllm,,acc,none,0.6437908496732027,0.01937333242072444,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_public_relations,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.04350271442923247,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_security_studies,5,lm-eval,vllm,,acc,none,0.7714285714285715,0.026882144922307713,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_social_sciences,5,lm-eval,vllm,yes,acc,none,0.745206369840754,0.0076950590141682245,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_sociology,5,lm-eval,vllm,,acc,none,0.8308457711442786,0.026508590656233278,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_stem,5,lm-eval,vllm,yes,acc,none,0.5737392959086585,0.008380391612755106,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_virology,5,lm-eval,vllm,,acc,none,0.4759036144578313,0.03887971849597268,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_ro_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17a5951100_2026-10-07T16-08-25.590712.json,1791388954.4344075,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr,5,lm-eval,vllm,yes,acc,none,0.6099558467454779,0.003928537552768604,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.3,0.04605661864718382,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_anatomy,5,lm-eval,vllm,,acc,none,0.5851851851851851,0.04256193767901412,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_astronomy,5,lm-eval,vllm,,acc,none,0.6907894736842105,0.037610708698674764,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6566037735849056,0.02922452646912477,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_college_biology,5,lm-eval,vllm,,acc,none,0.75,0.03621034121889507,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_college_chemistry,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_college_computer_science,5,lm-eval,vllm,,acc,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_college_medicine,5,lm-eval,vllm,,acc,none,0.6127167630057804,0.03714325906302067,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_computer_security,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7063829787234043,0.02977164271249127,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.5724137931034483,0.041227371113703344,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4365079365079365,0.025542846817400516,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_formal_logic,5,lm-eval,vllm,,acc,none,0.48412698412698413,0.044698818540726104,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_global_facts,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8,0.02275520495954297,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5369458128078818,0.03508370520442665,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7515151515151515,0.03374402644139407,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_geography,5,lm-eval,vllm,,acc,none,0.797979797979798,0.02860620428922983,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8341968911917098,0.026839845022314426,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7128205128205128,0.022939925418530637,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.35555555555555557,0.029185714949857472,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7563025210084033,0.027886828078380516,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_physics,5,lm-eval,vllm,,acc,none,0.4900662251655629,0.040816771072484305,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8018348623853211,0.017090573804217808,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.03350991604696042,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7598039215686274,0.029983733055913633,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8059071729957806,0.025744902532290916,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_human_aging,5,lm-eval,vllm,,acc,none,0.6771300448430493,0.031381476375754995,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_human_sexuality,5,lm-eval,vllm,,acc,none,0.6946564885496184,0.04039314978724566,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_humanities,5,lm-eval,vllm,yes,acc,none,0.5517534537725823,0.0068896186933052155,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_international_law,5,lm-eval,vllm,,acc,none,0.7851239669421488,0.037494924487096966,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_jurisprudence,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.0448993107359131,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6441717791411042,0.03761521380046734,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_machine_learning,5,lm-eval,vllm,,acc,none,0.4732142857142857,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_management,5,lm-eval,vllm,,acc,none,0.7184466019417476,0.044532548363264673,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_miscellaneous,5,lm-eval,vllm,,acc,none,0.6411238825031929,0.017152991797501307,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_moral_disputes,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.024946792225272324,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3553072625698324,0.016006989934803203,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_nutrition,5,lm-eval,vllm,,acc,none,0.6993464052287581,0.026256053835718912,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_other,5,lm-eval,vllm,yes,acc,none,0.6247183778564531,0.00847915717120347,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_philosophy,5,lm-eval,vllm,,acc,none,0.729903536977492,0.02521804037341055,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_prehistory,5,lm-eval,vllm,,acc,none,0.6358024691358025,0.026774929899722324,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_professional_accounting,5,lm-eval,vllm,,acc,none,0.425531914893617,0.02949482760014435,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_professional_law,5,lm-eval,vllm,,acc,none,0.4445893089960887,0.012691575792657214,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_professional_medicine,5,lm-eval,vllm,,acc,none,0.5551470588235294,0.030187532060329314,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6225490196078431,0.019610851474880286,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_public_relations,5,lm-eval,vllm,,acc,none,0.6363636363636364,0.04607582090719978,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7296067598310042,0.007862037230166765,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_sociology,5,lm-eval,vllm,,acc,none,0.8308457711442786,0.026508590656233278,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_stem,5,lm-eval,vllm,yes,acc,none,0.5654931810973676,0.008469434975557591,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sr_world_religions,5,lm-eval,vllm,,acc,none,0.7017543859649122,0.03508771929824561,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/996aaff981_2026-10-07T16-08-12.172029.json,1791388941.8015695,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv,5,lm-eval,vllm,yes,acc,none,0.6247685514883919,0.0038463499794870837,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_abstract_algebra,5,lm-eval,vllm,,acc,none,0.33,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_anatomy,5,lm-eval,vllm,,acc,none,0.562962962962963,0.042849586397534056,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_astronomy,5,lm-eval,vllm,,acc,none,0.7039473684210527,0.037150621549989084,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_business_ethics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6754716981132075,0.02881561571343209,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_college_biology,5,lm-eval,vllm,,acc,none,0.7708333333333334,0.03514697467862389,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_college_chemistry,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_college_computer_science,5,lm-eval,vllm,,acc,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_college_medicine,5,lm-eval,vllm,,acc,none,0.6358381502890174,0.03669072477416912,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7021276595744681,0.029896145682095487,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_econometrics,5,lm-eval,vllm,,acc,none,0.43859649122807015,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6344827586206897,0.04013124195424389,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4523809523809524,0.025634258115554927,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_formal_logic,5,lm-eval,vllm,,acc,none,0.49206349206349204,0.04471572536294351,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_global_facts,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_biology,5,lm-eval,vllm,,acc,none,0.8225806451612904,0.021732540689329255,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5763546798029556,0.03476725747649036,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_geography,5,lm-eval,vllm,,acc,none,0.8232323232323232,0.027178752639044908,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8393782383419689,0.02649905770139739,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7256410256410256,0.022622765767493235,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.3148148148148148,0.02831753349606653,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.773109243697479,0.02720537153827948,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_physics,5,lm-eval,vllm,,acc,none,0.4900662251655629,0.040816771072484305,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_psychology,5,lm-eval,vllm,,acc,none,0.7963302752293578,0.017266742087630755,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6157407407407407,0.03317354514310747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7892156862745098,0.028626547912437423,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8185654008438819,0.025085961144579647,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_human_aging,5,lm-eval,vllm,,acc,none,0.7085201793721974,0.03050028317654591,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_humanities,5,lm-eval,vllm,yes,acc,none,0.5540913921360255,0.006696326659620723,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6871165644171779,0.03642914578292403,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_machine_learning,5,lm-eval,vllm,,acc,none,0.44642857142857145,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_marketing,5,lm-eval,vllm,,acc,none,0.8504273504273504,0.023365051491753757,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_medical_genetics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_miscellaneous,5,lm-eval,vllm,,acc,none,0.7305236270753512,0.01586624307321501,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_moral_disputes,5,lm-eval,vllm,,acc,none,0.7023121387283237,0.024617055388677027,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3106145251396648,0.01547651543800557,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_nutrition,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.024848018263875137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_other,5,lm-eval,vllm,yes,acc,none,0.668490505310589,0.008221269098277043,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_prehistory,5,lm-eval,vllm,,acc,none,0.7469135802469136,0.02419180860071302,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_professional_accounting,5,lm-eval,vllm,,acc,none,0.42907801418439717,0.029525914302558586,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_professional_law,5,lm-eval,vllm,,acc,none,0.4198174706649283,0.012604960816087503,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_professional_medicine,5,lm-eval,vllm,,acc,none,0.6176470588235294,0.029520095697687675,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_professional_psychology,5,lm-eval,vllm,,acc,none,0.6421568627450981,0.019393058402355487,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_security_studies,5,lm-eval,vllm,,acc,none,0.7591836734693878,0.027372942201788125,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7403314917127072,0.007755197461395128,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_stem,5,lm-eval,vllm,yes,acc,none,0.5743736124326039,0.008407224658119442,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_sv_world_religions,5,lm-eval,vllm,,acc,none,0.783625730994152,0.03158149539338735,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4aa0098e3d_2026-10-07T15-55-59.274055.json,1791388218.2109892,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr,5,lm-eval,vllm,yes,acc,none,0.5947870673693206,0.0039510164969559156,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.31,0.04648231987117317,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_astronomy,5,lm-eval,vllm,,acc,none,0.7039473684210527,0.037150621549989084,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6339622641509434,0.02964781353936531,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_college_biology,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.037455547914624555,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_college_chemistry,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_college_computer_science,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_college_mathematics,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_college_medicine,5,lm-eval,vllm,,acc,none,0.6358381502890174,0.03669072477416912,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_college_physics,5,lm-eval,vllm,,acc,none,0.3333333333333333,0.04690650298201946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_computer_security,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6,0.03202563076101743,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_econometrics,5,lm-eval,vllm,,acc,none,0.45614035087719296,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6,0.040824829046386304,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.4523809523809524,0.025634258115554927,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_formal_logic,5,lm-eval,vllm,,acc,none,0.46825396825396826,0.04463112720677173,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_biology,5,lm-eval,vllm,,acc,none,0.7870967741935484,0.023287665127268594,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5320197044334976,0.03510766597959214,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7454545454545455,0.03401506715249038,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7676767676767676,0.030088629490217438,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.6994818652849741,0.033088185944157515,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6820512820512821,0.023610884308927833,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.34814814814814815,0.02904560029061618,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7436974789915967,0.028359620870533925,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_physics,5,lm-eval,vllm,,acc,none,0.4503311258278146,0.040622900186837764,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8055045871559633,0.016970289090458102,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5694444444444444,0.03376922151252338,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7892156862745098,0.028626547912437423,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7721518987341772,0.027303484599069387,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_human_aging,5,lm-eval,vllm,,acc,none,0.6591928251121076,0.03181149747055356,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_human_sexuality,5,lm-eval,vllm,,acc,none,0.6564885496183206,0.041649760719448814,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_humanities,5,lm-eval,vllm,yes,acc,none,0.5392136025504782,0.006844313711731766,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_international_law,5,lm-eval,vllm,,acc,none,0.8760330578512396,0.030083098716035202,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_jurisprudence,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.044531975073749855,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6073619631901841,0.038367409078310266,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_machine_learning,5,lm-eval,vllm,,acc,none,0.42857142857142855,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_management,5,lm-eval,vllm,,acc,none,0.7184466019417476,0.044532548363264673,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_medical_genetics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_miscellaneous,5,lm-eval,vllm,,acc,none,0.669220945083014,0.016824818462563704,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_moral_disputes,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.024946792225272324,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3329608938547486,0.015761716178397635,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_nutrition,5,lm-eval,vllm,,acc,none,0.6928104575163399,0.02641560191438905,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_other,5,lm-eval,vllm,yes,acc,none,0.6340521403282909,0.008448078099754616,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_philosophy,5,lm-eval,vllm,,acc,none,0.684887459807074,0.026385273703464482,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_prehistory,5,lm-eval,vllm,,acc,none,0.654320987654321,0.02646248777700184,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_professional_accounting,5,lm-eval,vllm,,acc,none,0.4219858156028369,0.029462189233370586,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_professional_law,5,lm-eval,vllm,,acc,none,0.42046936114732725,0.012607654553832918,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6286764705882353,0.029349803139765818,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_professional_psychology,5,lm-eval,vllm,,acc,none,0.5637254901960784,0.020062874243539024,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_public_relations,5,lm-eval,vllm,,acc,none,0.5727272727272728,0.04738198703545482,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_security_studies,5,lm-eval,vllm,,acc,none,0.710204081632653,0.029043088683304373,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.6915827104322392,0.008145889310934771,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_sociology,5,lm-eval,vllm,,acc,none,0.7711442786069652,0.0297052840567725,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_stem,5,lm-eval,vllm,yes,acc,none,0.5445607358071678,0.008533257613331078,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_virology,5,lm-eval,vllm,,acc,none,0.4759036144578313,0.03887971849597268,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_tr_world_religions,5,lm-eval,vllm,,acc,none,0.7309941520467836,0.03401052620104092,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0d47cc141_2026-10-07T16-18-31.631030.json,1791389564.0176902,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk,5,lm-eval,vllm,yes,acc,none,0.6158666856573137,0.003908477049818888,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_abstract_algebra,5,lm-eval,vllm,,acc,none,0.34,0.04760952285695233,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_anatomy,5,lm-eval,vllm,,acc,none,0.5185185185185185,0.043163785995113245,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_astronomy,5,lm-eval,vllm,,acc,none,0.7368421052631579,0.03583496176361067,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6528301886792452,0.02930010170554966,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_college_biology,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.037455547914624555,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_college_medicine,5,lm-eval,vllm,,acc,none,0.6705202312138728,0.03583901754736415,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_college_physics,5,lm-eval,vllm,,acc,none,0.43137254901960786,0.049280995972875316,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7063829787234043,0.02977164271249127,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_econometrics,5,lm-eval,vllm,,acc,none,0.45614035087719296,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6413793103448275,0.03996629574876715,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.455026455026455,0.025646928361049343,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_formal_logic,5,lm-eval,vllm,,acc,none,0.5238095238095238,0.04467062628403266,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_biology,5,lm-eval,vllm,,acc,none,0.8193548387096774,0.021886178567172513,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5566502463054187,0.03495334582162933,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7818181818181819,0.032250781083062896,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_geography,5,lm-eval,vllm,,acc,none,0.8232323232323232,0.027178752639044908,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8186528497409327,0.027807032360686077,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7128205128205128,0.022939925418530637,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.36666666666666664,0.029381620726464993,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7310924369747899,0.028801392193631228,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8073394495412844,0.0169092768849361,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.03324708911809121,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7401960784313726,0.030778554678693247,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7974683544303798,0.02616056824660147,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_human_aging,5,lm-eval,vllm,,acc,none,0.6681614349775785,0.03160295143776678,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_human_sexuality,5,lm-eval,vllm,,acc,none,0.7099236641221374,0.03980066246467765,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_humanities,5,lm-eval,vllm,yes,acc,none,0.5538788522848034,0.006841234898753147,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_international_law,5,lm-eval,vllm,,acc,none,0.7851239669421488,0.037494924487096966,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_jurisprudence,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.044531975073749855,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6932515337423313,0.036230899157241474,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_machine_learning,5,lm-eval,vllm,,acc,none,0.4107142857142857,0.04669510663875191,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_management,5,lm-eval,vllm,,acc,none,0.6990291262135923,0.045416094465039504,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_marketing,5,lm-eval,vllm,,acc,none,0.8034188034188035,0.026035386098951282,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_miscellaneous,5,lm-eval,vllm,,acc,none,0.685823754789272,0.016599291735884803,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_moral_disputes,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.024405173935783293,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3139664804469274,0.015521923933523658,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_nutrition,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.025646863097137932,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_other,5,lm-eval,vllm,yes,acc,none,0.638236240746701,0.008417265117972294,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_philosophy,5,lm-eval,vllm,,acc,none,0.6720257234726688,0.02666441088693758,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_prehistory,5,lm-eval,vllm,,acc,none,0.6728395061728395,0.026105673861409787,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_professional_accounting,5,lm-eval,vllm,,acc,none,0.3971631205673759,0.029189805673587126,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_professional_law,5,lm-eval,vllm,,acc,none,0.46153846153846156,0.012732398286190275,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_professional_medicine,5,lm-eval,vllm,,acc,none,0.5882352941176471,0.02989616303312549,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_professional_psychology,5,lm-eval,vllm,,acc,none,0.6356209150326797,0.0194695182215738,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_public_relations,5,lm-eval,vllm,,acc,none,0.6272727272727273,0.04631381319425461,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_security_studies,5,lm-eval,vllm,,acc,none,0.7346938775510204,0.028263889943784655,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7296067598310042,0.007858035183123956,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_sociology,5,lm-eval,vllm,,acc,none,0.8258706467661692,0.026814951200421624,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_stem,5,lm-eval,vllm,yes,acc,none,0.575325087218522,0.008436145916194893,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_virology,5,lm-eval,vllm,,acc,none,0.4819277108433735,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_mmlu_full_uk_world_religions,5,lm-eval,vllm,,acc,none,0.7368421052631579,0.033773102522091994,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d510960049_2026-10-07T15-41-45.532357.json,1791387348.8811905,1 +v1annealC_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/df4b938f11_2026-10-07T15-47-03.573105.json,1791387861.913023,1 +v1annealC_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_bytes,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/df4b938f11_2026-10-07T15-47-03.573105.json,1791387861.913023,1 +v1annealC_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_norm,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/df4b938f11_2026-10-07T15-47-03.573105.json,1791387861.913023,1 +v1annealC_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b33115c0a4_2026-10-07T15-49-03.629156.json,1791387975.8865736,1 +v1annealC_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_bytes,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b33115c0a4_2026-10-07T15-49-03.629156.json,1791387975.8865736,1 +v1annealC_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_norm,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b33115c0a4_2026-10-07T15-49-03.629156.json,1791387975.8865736,1 +v1annealC_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/866cd139b0_2026-10-07T15-51-04.508056.json,1791388101.9445953,1 +v1annealC_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/866cd139b0_2026-10-07T15-51-04.508056.json,1791388101.9445953,1 +v1annealC_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/866cd139b0_2026-10-07T15-51-04.508056.json,1791388101.9445953,1 +v1annealC_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b60874a90a_2026-10-07T15-46-58.544265.json,1791387860.2616272,1 +v1annealC_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b60874a90a_2026-10-07T15-46-58.544265.json,1791387860.2616272,1 +v1annealC_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b60874a90a_2026-10-07T15-46-58.544265.json,1791387860.2616272,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a5d97a7d30_2026-10-07T16-15-29.216148.json,1791389557.8842406,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a5d97a7d30_2026-10-07T16-15-29.216148.json,1791389557.8842406,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a5d97a7d30_2026-10-07T16-15-29.216148.json,1791389557.8842406,1 +v1annealC_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c9963212cf_2026-10-07T15-52-57.981740.json,1791388217.5398397,1 +v1annealC_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_bytes,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c9963212cf_2026-10-07T15-52-57.981740.json,1791388217.5398397,1 +v1annealC_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c9963212cf_2026-10-07T15-52-57.981740.json,1791388217.5398397,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00e38ce7a8_2026-10-07T15-46-56.752804.json,1791387855.6530504,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_bytes,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00e38ce7a8_2026-10-07T15-46-56.752804.json,1791387855.6530504,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_norm,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00e38ce7a8_2026-10-07T15-46-56.752804.json,1791387855.6530504,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/316d89855e_2026-10-07T15-50-56.102430.json,1791388093.5831878,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/316d89855e_2026-10-07T15-50-56.102430.json,1791388093.5831878,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/316d89855e_2026-10-07T15-50-56.102430.json,1791388093.5831878,1 +v1annealC_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1fc82ef98d_2026-10-07T15-48-54.209693.json,1791387973.1668642,1 +v1annealC_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1fc82ef98d_2026-10-07T15-48-54.209693.json,1791387973.1668642,1 +v1annealC_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1fc82ef98d_2026-10-07T15-48-54.209693.json,1791387973.1668642,1 +v1annealC_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ad932a4bc0_2026-10-07T16-15-19.625551.json,1791389560.2432148,1 +v1annealC_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ad932a4bc0_2026-10-07T16-15-19.625551.json,1791389560.2432148,1 +v1annealC_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ad932a4bc0_2026-10-07T16-15-19.625551.json,1791389560.2432148,1 +v1annealC_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4cef676373_2026-10-07T15-52-58.533839.json,1791388218.781445,1 +v1annealC_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_bytes,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4cef676373_2026-10-07T15-52-58.533839.json,1791388218.781445,1 +v1annealC_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4cef676373_2026-10-07T15-52-58.533839.json,1791388218.781445,1 +v1annealC_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc3cd1099b_2026-10-07T16-27-31.792878.json,1791390290.3214357,1 +v1annealC_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc3cd1099b_2026-10-07T16-27-31.792878.json,1791390290.3214357,1 +v1annealC_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc3cd1099b_2026-10-07T16-27-31.792878.json,1791390290.3214357,1 +v1annealC_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d6fe9715c6_2026-10-07T16-19-27.828001.json,1791389805.9031382,1 +v1annealC_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d6fe9715c6_2026-10-07T16-19-27.828001.json,1791389805.9031382,1 +v1annealC_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d6fe9715c6_2026-10-07T16-19-27.828001.json,1791389805.9031382,1 +v1annealC_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dd5971d20_2026-10-07T16-21-34.466825.json,1791389931.8936763,1 +v1annealC_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_bytes,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dd5971d20_2026-10-07T16-21-34.466825.json,1791389931.8936763,1 +v1annealC_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dd5971d20_2026-10-07T16-21-34.466825.json,1791389931.8936763,1 +v1annealC_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/178df86928_2026-10-07T15-42-37.232514.json,1791387598.1920063,1 +v1annealC_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_bytes,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/178df86928_2026-10-07T15-42-37.232514.json,1791387598.1920063,1 +v1annealC_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_norm,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/178df86928_2026-10-07T15-42-37.232514.json,1791387598.1920063,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ced72d683e_2026-10-07T16-19-32.720794.json,1791389811.4718156,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ced72d683e_2026-10-07T16-19-32.720794.json,1791389811.4718156,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ced72d683e_2026-10-07T16-19-32.720794.json,1791389811.4718156,1 +v1annealC_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51c5cfa5f6_2026-10-07T15-38-28.228632.json,1791387349.9116085,1 +v1annealC_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_bytes,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51c5cfa5f6_2026-10-07T15-38-28.228632.json,1791387349.9116085,1 +v1annealC_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_norm,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51c5cfa5f6_2026-10-07T15-38-28.228632.json,1791387349.9116085,1 +v1annealC_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b118f27a04_2026-10-07T15-53-02.978465.json,1791388221.878232,1 +v1annealC_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b118f27a04_2026-10-07T15-53-02.978465.json,1791388221.878232,1 +v1annealC_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b118f27a04_2026-10-07T15-53-02.978465.json,1791388221.878232,1 +v1annealC_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb072e23a6_2026-10-07T16-03-06.934394.json,1791388827.8738947,1 +v1annealC_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb072e23a6_2026-10-07T16-03-06.934394.json,1791388827.8738947,1 +v1annealC_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb072e23a6_2026-10-07T16-03-06.934394.json,1791388827.8738947,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5371e18bc9_2026-10-07T15-51-00.577623.json,1791388095.3336425,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5371e18bc9_2026-10-07T15-51-00.577623.json,1791388095.3336425,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5371e18bc9_2026-10-07T15-51-00.577623.json,1791388095.3336425,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a5f5efc99e_2026-10-07T16-05-10.709954.json,1791388952.4852748,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_bytes,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a5f5efc99e_2026-10-07T16-05-10.709954.json,1791388952.4852748,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_norm,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a5f5efc99e_2026-10-07T16-05-10.709954.json,1791388952.4852748,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03b2333455_2026-10-07T16-01-00.290602.json,1791388704.3677702,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_bytes,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03b2333455_2026-10-07T16-01-00.290602.json,1791388704.3677702,1 +v1annealC_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03b2333455_2026-10-07T16-01-00.290602.json,1791388704.3677702,1 +v1annealC_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3f81cd8c1_2026-10-07T15-47-12.884533.json,1791387864.7668846,1 +v1annealC_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_bytes,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3f81cd8c1_2026-10-07T15-47-12.884533.json,1791387864.7668846,1 +v1annealC_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3f81cd8c1_2026-10-07T15-47-12.884533.json,1791387864.7668846,1 +v1annealC_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/987fe60f10_2026-10-07T15-53-03.519564.json,1791388223.0935566,1 +v1annealC_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_bytes,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/987fe60f10_2026-10-07T15-53-03.519564.json,1791388223.0935566,1 +v1annealC_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_norm,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/987fe60f10_2026-10-07T15-53-03.519564.json,1791388223.0935566,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/398af16196_2026-10-07T16-05-03.987735.json,1791388943.4399283,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_bytes,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/398af16196_2026-10-07T16-05-03.987735.json,1791388943.4399283,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/398af16196_2026-10-07T16-05-03.987735.json,1791388943.4399283,1 +v1annealC_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d5f3be7f6_2026-10-07T16-03-03.427091.json,1791388825.900528,1 +v1annealC_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d5f3be7f6_2026-10-07T16-03-03.427091.json,1791388825.900528,1 +v1annealC_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d5f3be7f6_2026-10-07T16-03-03.427091.json,1791388825.900528,1 +v1annealC_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5a3d671693_2026-10-07T16-21-38.401684.json,1791389937.478954,1 +v1annealC_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_bytes,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5a3d671693_2026-10-07T16-21-38.401684.json,1791389937.478954,1 +v1annealC_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_norm,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5a3d671693_2026-10-07T16-21-38.401684.json,1791389937.478954,1 +v1annealC_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/215d6db844_2026-10-07T15-38-30.003115.json,1791387349.3214455,1 +v1annealC_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/215d6db844_2026-10-07T15-38-30.003115.json,1791387349.3214455,1 +v1annealC_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/215d6db844_2026-10-07T15-38-30.003115.json,1791387349.3214455,1 +v1annealC_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc,none,0.91,0.028762349126466136,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5cc96cc081_2026-10-07T16-03-07.503616.json,1791388826.8470078,1 +v1annealC_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5cc96cc081_2026-10-07T16-03-07.503616.json,1791388826.8470078,1 +v1annealC_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_norm,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5cc96cc081_2026-10-07T16-03-07.503616.json,1791388826.8470078,1 +v1annealC_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a546feeef7_2026-10-07T15-47-05.922829.json,1791387865.069063,1 +v1annealC_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a546feeef7_2026-10-07T15-47-05.922829.json,1791387865.069063,1 +v1annealC_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a546feeef7_2026-10-07T15-47-05.922829.json,1791387865.069063,1 +v1annealC_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d7223335c_2026-10-07T16-17-25.334353.json,1791389683.13001,1 +v1annealC_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_bytes,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d7223335c_2026-10-07T16-17-25.334353.json,1791389683.13001,1 +v1annealC_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d7223335c_2026-10-07T16-17-25.334353.json,1791389683.13001,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c42b349308_2026-10-07T16-03-13.234465.json,1791388831.3011959,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c42b349308_2026-10-07T16-03-13.234465.json,1791388831.3011959,1 +v1annealC_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c42b349308_2026-10-07T16-03-13.234465.json,1791388831.3011959,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_als_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/501a9b3d24_2026-10-07T16-01-04.526000.json,1791388700.4823256,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_bos_latn,0,lm-eval,vllm,,exact_match,strict_match,0.7,0.046056618647183814,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a61acc919b_2026-10-07T15-50-55.631662.json,1791388087.119096,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_bul_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.51,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c8bbfb9a82_2026-10-07T15-51-03.512836.json,1791388091.7752585,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_cat_latn,0,lm-eval,vllm,,exact_match,strict_match,0.37,0.048523658709391,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5980acb07e_2026-10-07T15-49-06.304603.json,1791387964.0767932,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_ces_latn,0,lm-eval,vllm,,exact_match,strict_match,0.51,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bc31d76090_2026-10-07T15-50-54.164783.json,1791388086.9626079,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_deu_latn,0,lm-eval,vllm,,exact_match,strict_match,0.51,0.05024183937956911,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/249036ff35_2026-10-07T15-47-08.030396.json,1791387861.0907958,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_ekk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001975,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/298c1705cd_2026-10-07T15-46-58.112682.json,1791387855.205458,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_ell_grek,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.04923659639173309,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/de52cf3690_2026-10-07T16-05-24.419166.json,1791388956.8095717,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_eng_latn,0,lm-eval,vllm,,exact_match,strict_match,0.35,0.0479372485441102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c471c0902b_2026-10-07T16-01-04.980851.json,1791388700.8424187,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_fin_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/19058f4ac9_2026-10-07T16-27-47.110841.json,1791390289.8805838,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_fra_latn_fran,0,lm-eval,vllm,,exact_match,strict_match,0.56,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9b1dd0d537_2026-10-07T15-38-31.442764.json,1791387347.7962809,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_glg_latn,0,lm-eval,vllm,,exact_match,strict_match,0.53,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4214b7ce00_2026-10-07T15-48-57.248380.json,1791387970.262235,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_hrv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/370a83c402_2026-10-07T15-53-07.787539.json,1791388218.3855238,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_hun_latn,0,lm-eval,vllm,,exact_match,strict_match,0.56,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9a4d06d3a1_2026-10-07T16-17-35.814685.json,1791389684.4313214,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_isl_latn,0,lm-eval,vllm,,exact_match,strict_match,0.51,0.05024183937956911,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2312d5091d_2026-10-07T16-03-15.982523.json,1791388827.843997,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_ita_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ad0bd0058_2026-10-07T15-47-05.006437.json,1791387855.1897402,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_kat_geor,0,lm-eval,vllm,,exact_match,strict_match,0.33,0.047258156262526045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2036854bf8_2026-10-07T16-19-37.462890.json,1791389805.6614249,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_lit_latn,0,lm-eval,vllm,,exact_match,strict_match,0.51,0.05024183937956911,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/384df7a5d7_2026-10-07T16-01-09.297491.json,1791388705.8199968,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_mkd_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956911,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b7c23ec172_2026-10-07T16-05-14.040023.json,1791388947.1035545,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_nld_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cad174514b_2026-10-07T16-05-17.266254.json,1791388942.9752827,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_nno_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.049431107042371025,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d913065e08_2026-10-07T16-03-11.839989.json,1791388829.449658,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_nob_latn,0,lm-eval,vllm,,exact_match,strict_match,0.54,0.05009082659620333,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a18bd8d7d5_2026-10-07T16-19-41.179725.json,1791389807.0803323,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_pol_latn,0,lm-eval,vllm,,exact_match,strict_match,0.44,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f8205aac7_2026-10-07T15-53-13.038157.json,1791388218.4991634,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_por_latn_port,0,lm-eval,vllm,,exact_match,strict_match,0.53,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/057969291b_2026-10-07T15-38-40.237096.json,1791387349.904812,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_ron_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d55cd5e096_2026-10-07T16-05-04.721967.json,1791388943.611979,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_slk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/50786b0ef3_2026-10-07T15-48-52.902766.json,1791387965.3593178,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_slv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9317487036_2026-10-07T15-48-53.223723.json,1791387971.4360328,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_spa_latn_spai,0,lm-eval,vllm,,exact_match,strict_match,0.53,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/33e59b77b2_2026-10-07T16-05-17.910626.json,1791388948.5113704,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_srp_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.04943110704237102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/16bcb63f82_2026-10-07T16-01-12.459903.json,1791388701.7448575,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_swe_latn,0,lm-eval,vllm,,exact_match,strict_match,0.55,0.04999999999999999,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e766081597_2026-10-07T16-03-39.831097.json,1791388834.730331,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_tur_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/95a4cb9fc0_2026-10-07T16-19-25.448993.json,1791389803.1162996,1 +v1annealC_merge3_116k_120k,global_piqa_prompted_ukr_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.32,0.046882617226215034,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/651215447a_2026-10-07T16-19-33.606383.json,1791389807.2449756,1 +v1annealC_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,flexible-extract,0.6595905989385898,0.013052097103299095,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b874b22e24_2026-10-07T15-48-06.853794.json,1791387859.2196703,1 +v1annealC_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,strict-match,0.6580742987111448,0.013066089625182813,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b874b22e24_2026-10-07T15-48-06.853794.json,1791387859.2196703,1 +v1annealC_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc,none,0.5928101971718781,0.004903066639762152,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc67c86780_2026-10-07T16-20-52.185669.json,1791389805.1957853,1 +v1annealC_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc_norm,none,0.7922724556861183,0.004048515801613888,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc67c86780_2026-10-07T16-20-52.185669.json,1791389805.1957853,1 +v1annealC_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc,none,0.59699263095001,0.004894997736719122,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/25a8cc3d2c_2026-10-07T15-53-44.676714.json,1791387856.129295,1 +v1annealC_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc_norm,none,0.8002389962158932,0.003990035207014982,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/25a8cc3d2c_2026-10-07T15-53-44.676714.json,1791387856.129295,1 +v1annealC_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc,none,0.5050483118011073,0.005209764015945573,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4307ab3575_2026-10-07T16-02-30.647296.json,1791388699.3906927,1 +v1annealC_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc_norm,none,0.6711540549343177,0.004895280022795303,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4307ab3575_2026-10-07T16-02-30.647296.json,1791388699.3906927,1 +v1annealC_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc,none,0.5351961311123052,0.005170785222242978,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a630f4d7fb_2026-10-07T16-06-35.837340.json,1791388942.8673513,1 +v1annealC_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc_norm,none,0.6958624395486298,0.00476937944671591,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a630f4d7fb_2026-10-07T16-06-35.837340.json,1791388942.8673513,1 +v1annealC_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc,none,0.5298889837745516,0.0051569438102257855,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e346c4be4_2026-10-07T15-52-27.466067.json,1791388097.8166132,1 +v1annealC_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc_norm,none,0.6858454312553374,0.004796059417691675,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e346c4be4_2026-10-07T15-52-27.466067.json,1791388097.8166132,1 +v1annealC_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc,none,0.552912310646469,0.0051355288952797075,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69da83ed1b_2026-10-07T15-40-02.947735.json,1791387355.37542,1 +v1annealC_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc_norm,none,0.7391721783656924,0.004535346311841642,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69da83ed1b_2026-10-07T15-40-02.947735.json,1791387355.37542,1 +v1annealC_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc,none,0.3038357644516478,0.0047809098342103925,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/68a75c6ce8_2026-10-07T16-28-59.052570.json,1791390287.2378268,1 +v1annealC_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc_norm,none,0.3620745542949757,0.004995963049653421,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/68a75c6ce8_2026-10-07T16-28-59.052570.json,1791390287.2378268,1 +v1annealC_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc,none,0.5455129578068109,0.0051529936695425774,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75ce2c54c8_2026-10-07T15-40-06.070917.json,1791387349.0753126,1 +v1annealC_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc_norm,none,0.7263868065967016,0.004613694264571839,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75ce2c54c8_2026-10-07T15-40-06.070917.json,1791387349.0753126,1 +v1annealC_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc,none,0.4938232499208109,0.005137618755731682,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38da5b20ba_2026-10-07T15-52-28.978916.json,1791388093.6974669,1 +v1annealC_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc_norm,none,0.6589589272516102,0.00487144188996751,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38da5b20ba_2026-10-07T15-52-28.978916.json,1791388093.6974669,1 +v1annealC_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc,none,0.4480754468691743,0.005207935977577042,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c166b642f6_2026-10-07T16-23-13.562431.json,1791389936.832077,1 +v1annealC_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc_norm,none,0.5853712029827832,0.005159357403791309,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c166b642f6_2026-10-07T16-23-13.562431.json,1791389936.832077,1 +v1annealC_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc,none,0.5318176873708256,0.005204558351051597,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9356b157f7_2026-10-07T16-22-43.648419.json,1791389926.6174986,1 +v1annealC_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc_norm,none,0.7089089524638311,0.004738104632341199,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9356b157f7_2026-10-07T16-22-43.648419.json,1791389926.6174986,1 +v1annealC_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc,none,0.533405288720993,0.005183215807803298,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/45d50f9795_2026-10-07T15-52-15.545490.json,1791388093.415348,1 +v1annealC_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc_norm,none,0.6958445763626552,0.004779743955343341,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/45d50f9795_2026-10-07T15-52-15.545490.json,1791388093.415348,1 +v1annealC_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc,none,0.5407953191028281,0.005187592123876334,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e493bf2b43_2026-10-07T15-50-17.399434.json,1791387969.8358018,1 +v1annealC_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc_norm,none,0.7186043991765089,0.0046811202189423985,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e493bf2b43_2026-10-07T15-50-17.399434.json,1791387969.8358018,1 +v1annealC_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc,none,0.5129259058950785,0.005198701292371326,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8fd9384f2_2026-10-07T16-21-10.171137.json,1791389805.9203527,1 +v1annealC_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc_norm,none,0.6723634396971336,0.004881668177003551,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8fd9384f2_2026-10-07T16-21-10.171137.json,1791389805.9203527,1 +v1annealC_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc,none,0.4735898787559304,0.0051270499546463575,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a561e1e2f8_2026-10-07T15-50-31.883000.json,1791387973.0324762,1 +v1annealC_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc_norm,none,0.6150764364786505,0.004996386439551018,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a561e1e2f8_2026-10-07T15-50-31.883000.json,1791387973.0324762,1 +v1annealC_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc,none,0.49825378346915017,0.0051439579940964035,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4fe87c0f6e_2026-10-07T16-06-36.333840.json,1791388947.4430997,1 +v1annealC_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc_norm,none,0.6531908138427347,0.004896608567249327,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4fe87c0f6e_2026-10-07T16-06-36.333840.json,1791388947.4430997,1 +v1annealC_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc,none,0.5315720236790178,0.005224939218682111,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cd778a5469_2026-10-07T15-54-25.146480.json,1791388218.1986055,1 +v1annealC_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc_norm,none,0.6976540232405174,0.004808957297377342,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cd778a5469_2026-10-07T15-54-25.146480.json,1791388218.1986055,1 +v1annealC_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc,none,0.4706132426400255,0.005146002040376644,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8248b05a90_2026-10-07T16-29-17.512152.json,1791390287.7021747,1 +v1annealC_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc_norm,none,0.6096290785418217,0.0050294779978137145,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8248b05a90_2026-10-07T16-29-17.512152.json,1791390287.7021747,1 +v1annealC_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_loose_acc,none,0.42565947242206237,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/541200478f_2026-10-07T16-17-05.503429.json,1791389565.043799,1 +v1annealC_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_strict_acc,none,0.3932853717026379,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/541200478f_2026-10-07T16-17-05.503429.json,1791389565.043799,1 +v1annealC_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_loose_acc,none,0.30868761552680224,0.019879245251116444,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/541200478f_2026-10-07T16-17-05.503429.json,1791389565.043799,1 +v1annealC_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_strict_acc,none,0.2680221811460259,0.019060638691630338,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/541200478f_2026-10-07T16-17-05.503429.json,1791389565.043799,1 +v1annealC_merge3_116k_120k,include_base_44_albanian,0,lm-eval,vllm,yes,acc,none,0.7041742286751361,0.019330063234607498,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eb8e45bbb_2026-10-07T16-05-11.606739.json,1791388951.070108,1 +v1annealC_merge3_116k_120k,include_base_44_albanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.7130044843049327,0.030360379710291947,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eb8e45bbb_2026-10-07T16-05-11.606739.json,1791388951.070108,1 +v1annealC_merge3_116k_120k,include_base_44_albanian_business_commerce,0,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eb8e45bbb_2026-10-07T16-05-11.606739.json,1791388951.070108,1 +v1annealC_merge3_116k_120k,include_base_44_albanian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.52,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eb8e45bbb_2026-10-07T16-05-11.606739.json,1791388951.070108,1 +v1annealC_merge3_116k_120k,include_base_44_albanian_social_science,0,lm-eval,vllm,,acc,none,0.7272727272727273,0.0606060606060606,55,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eb8e45bbb_2026-10-07T16-05-11.606739.json,1791388951.070108,1 +v1annealC_merge3_116k_120k,include_base_44_albanian_stem,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eb8e45bbb_2026-10-07T16-05-11.606739.json,1791388951.070108,1 +v1annealC_merge3_116k_120k,include_base_44_basque,0,lm-eval,vllm,yes,acc,none,0.446,0.022252153078595936,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4050fff5a5_2026-10-07T16-27-32.149750.json,1791390289.2718668,1 +v1annealC_merge3_116k_120k,include_base_44_basque_professional_certification,0,lm-eval,vllm,,acc,none,0.446,0.022252153078595936,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4050fff5a5_2026-10-07T16-27-32.149750.json,1791390289.2718668,1 +v1annealC_merge3_116k_120k,include_base_44_bulgarian,0,lm-eval,vllm,yes,acc,none,0.6527272727272727,0.01996007315931429,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3bf67c9af8_2026-10-07T15-47-06.003389.json,1791387856.3096824,1 +v1annealC_merge3_116k_120k,include_base_44_bulgarian_arts_humanities,0,lm-eval,vllm,,acc,none,0.752,0.027367497504863593,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3bf67c9af8_2026-10-07T15-47-06.003389.json,1791387856.3096824,1 +v1annealC_merge3_116k_120k,include_base_44_bulgarian_social_science,0,lm-eval,vllm,,acc,none,0.584,0.031235856237014505,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3bf67c9af8_2026-10-07T15-47-06.003389.json,1791387856.3096824,1 +v1annealC_merge3_116k_120k,include_base_44_bulgarian_stem,0,lm-eval,vllm,,acc,none,0.5,0.07142857142857142,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3bf67c9af8_2026-10-07T15-47-06.003389.json,1791387856.3096824,1 +v1annealC_merge3_116k_120k,include_base_44_croatian,0,lm-eval,vllm,yes,acc,none,0.7218181818181818,0.018941579841725155,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/636e95f4d7_2026-10-07T15-38-32.737371.json,1791387349.3531103,1 +v1annealC_merge3_116k_120k,include_base_44_croatian_arts_humanities,0,lm-eval,vllm,,acc,none,0.676,0.029658294924545567,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/636e95f4d7_2026-10-07T15-38-32.737371.json,1791387349.3531103,1 +v1annealC_merge3_116k_120k,include_base_44_croatian_social_science,0,lm-eval,vllm,,acc,none,0.792,0.025721398901416368,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/636e95f4d7_2026-10-07T15-38-32.737371.json,1791387349.3531103,1 +v1annealC_merge3_116k_120k,include_base_44_croatian_stem,0,lm-eval,vllm,,acc,none,0.6,0.06998542122237651,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/636e95f4d7_2026-10-07T15-38-32.737371.json,1791387349.3531103,1 +v1annealC_merge3_116k_120k,include_base_44_dutch,0,lm-eval,vllm,yes,acc,none,0.6460980036297641,0.020260205536703872,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38f66d9100_2026-10-07T15-51-02.269618.json,1791388099.141331,1 +v1annealC_merge3_116k_120k,include_base_44_dutch_applied_science,0,lm-eval,vllm,,acc,none,0.8666666666666667,0.09085135251589958,15,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38f66d9100_2026-10-07T15-51-02.269618.json,1791388099.141331,1 +v1annealC_merge3_116k_120k,include_base_44_dutch_arts_humanities,0,lm-eval,vllm,,acc,none,0.6502057613168725,0.03065660440535111,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38f66d9100_2026-10-07T15-51-02.269618.json,1791388099.141331,1 +v1annealC_merge3_116k_120k,include_base_44_dutch_health_oriented_education,0,lm-eval,vllm,,acc,none,0.4,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38f66d9100_2026-10-07T15-51-02.269618.json,1791388099.141331,1 +v1annealC_merge3_116k_120k,include_base_44_dutch_social_science,0,lm-eval,vllm,,acc,none,0.6625514403292181,0.03039526314545395,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38f66d9100_2026-10-07T15-51-02.269618.json,1791388099.141331,1 +v1annealC_merge3_116k_120k,include_base_44_dutch_stem,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38f66d9100_2026-10-07T15-51-02.269618.json,1791388099.141331,1 +v1annealC_merge3_116k_120k,include_base_44_estonian,0,lm-eval,vllm,yes,acc,none,0.5133928571428571,0.03257799668524996,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8985175333_2026-10-07T16-15-19.057935.json,1791389558.1218138,1 +v1annealC_merge3_116k_120k,include_base_44_estonian_applied_science,0,lm-eval,vllm,,acc,none,0.6428571428571429,0.13289435848843764,14,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8985175333_2026-10-07T16-15-19.057935.json,1791389558.1218138,1 +v1annealC_merge3_116k_120k,include_base_44_estonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.453416149068323,0.03935653891289661,161,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8985175333_2026-10-07T16-15-19.057935.json,1791389558.1218138,1 +v1annealC_merge3_116k_120k,include_base_44_estonian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.0,0.0,2,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8985175333_2026-10-07T16-15-19.057935.json,1791389558.1218138,1 +v1annealC_merge3_116k_120k,include_base_44_estonian_social_science,0,lm-eval,vllm,,acc,none,0.45454545454545453,0.1574591643244434,11,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8985175333_2026-10-07T16-15-19.057935.json,1791389558.1218138,1 +v1annealC_merge3_116k_120k,include_base_44_estonian_stem,0,lm-eval,vllm,,acc,none,0.7777777777777778,0.07027283689263066,36,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8985175333_2026-10-07T16-15-19.057935.json,1791389558.1218138,1 +v1annealC_merge3_116k_120k,include_base_44_finnish,0,lm-eval,vllm,yes,acc,none,0.5172413793103449,0.021323839011610835,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fe2d2b3e2_2026-10-07T15-38-36.632363.json,1791387354.6228142,1 +v1annealC_merge3_116k_120k,include_base_44_finnish_applied_science,0,lm-eval,vllm,,acc,none,0.6206896551724138,0.09169709590633639,29,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fe2d2b3e2_2026-10-07T15-38-36.632363.json,1791387354.6228142,1 +v1annealC_merge3_116k_120k,include_base_44_finnish_arts_humanities,0,lm-eval,vllm,,acc,none,0.49557522123893805,0.0333320280633051,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fe2d2b3e2_2026-10-07T15-38-36.632363.json,1791387354.6228142,1 +v1annealC_merge3_116k_120k,include_base_44_finnish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5777777777777777,0.07446027270295803,45,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fe2d2b3e2_2026-10-07T15-38-36.632363.json,1791387354.6228142,1 +v1annealC_merge3_116k_120k,include_base_44_finnish_social_science,0,lm-eval,vllm,,acc,none,0.504424778761062,0.0333320280633051,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fe2d2b3e2_2026-10-07T15-38-36.632363.json,1791387354.6228142,1 +v1annealC_merge3_116k_120k,include_base_44_finnish_stem,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fe2d2b3e2_2026-10-07T15-38-36.632363.json,1791387354.6228142,1 +v1annealC_merge3_116k_120k,include_base_44_french,0,lm-eval,vllm,yes,acc,none,0.6085918854415274,0.023642409383541983,419,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/935812a807_2026-10-07T15-53-08.336189.json,1791388223.0835683,1 +v1annealC_merge3_116k_120k,include_base_44_french_arts_humanities,0,lm-eval,vllm,,acc,none,0.6654135338345865,0.028985250824771575,266,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/935812a807_2026-10-07T15-53-08.336189.json,1791388223.0835683,1 +v1annealC_merge3_116k_120k,include_base_44_french_driving_license,0,lm-eval,vllm,,acc,none,0.574468085106383,0.07289875413448861,47,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/935812a807_2026-10-07T15-53-08.336189.json,1791388223.0835683,1 +v1annealC_merge3_116k_120k,include_base_44_french_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5,0.12909944487358055,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/935812a807_2026-10-07T15-53-08.336189.json,1791388223.0835683,1 +v1annealC_merge3_116k_120k,include_base_44_french_social_science,0,lm-eval,vllm,,acc,none,0.5,0.058520573598065284,74,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/935812a807_2026-10-07T15-53-08.336189.json,1791388223.0835683,1 +v1annealC_merge3_116k_120k,include_base_44_french_stem,0,lm-eval,vllm,,acc,none,0.375,0.125,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/935812a807_2026-10-07T15-53-08.336189.json,1791388223.0835683,1 +v1annealC_merge3_116k_120k,include_base_44_georgian,0,lm-eval,vllm,yes,acc,none,0.332,0.021081766571222797,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e357d8d8c2_2026-10-07T16-19-31.970019.json,1791389803.0012534,1 +v1annealC_merge3_116k_120k,include_base_44_georgian_arts_humanities,0,lm-eval,vllm,,acc,none,0.332,0.021081766571222797,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e357d8d8c2_2026-10-07T16-19-31.970019.json,1791389803.0012534,1 +v1annealC_merge3_116k_120k,include_base_44_german,0,lm-eval,vllm,yes,acc,none,0.48201438848920863,0.04277861986940414,139,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/32c9d68d3e_2026-10-07T15-48-43.733950.json,1791387963.1145022,1 +v1annealC_merge3_116k_120k,include_base_44_german_driving_license,0,lm-eval,vllm,,acc,none,0.5217391304347826,0.10649955403405124,23,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/32c9d68d3e_2026-10-07T15-48-43.733950.json,1791387963.1145022,1 +v1annealC_merge3_116k_120k,include_base_44_german_social_science,0,lm-eval,vllm,,acc,none,0.46153846153846156,0.05254846546645948,91,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/32c9d68d3e_2026-10-07T15-48-43.733950.json,1791387963.1145022,1 +v1annealC_merge3_116k_120k,include_base_44_german_stem,0,lm-eval,vllm,,acc,none,0.52,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/32c9d68d3e_2026-10-07T15-48-43.733950.json,1791387963.1145022,1 +v1annealC_merge3_116k_120k,include_base_44_greek,0,lm-eval,vllm,yes,acc,none,0.5507246376811594,0.020972773991378445,552,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ec8333914_2026-10-07T16-03-13.062373.json,1791388830.7417545,1 +v1annealC_merge3_116k_120k,include_base_44_greek_arts_humanities,0,lm-eval,vllm,,acc,none,0.5135135135135135,0.08330289193201319,37,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ec8333914_2026-10-07T16-03-13.062373.json,1791388830.7417545,1 +v1annealC_merge3_116k_120k,include_base_44_greek_business_commerce,0,lm-eval,vllm,,acc,none,0.7142857142857143,0.057372809207321344,63,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ec8333914_2026-10-07T16-03-13.062373.json,1791388830.7417545,1 +v1annealC_merge3_116k_120k,include_base_44_greek_health_oriented_education,0,lm-eval,vllm,,acc,none,0.28,0.0916515138991168,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ec8333914_2026-10-07T16-03-13.062373.json,1791388830.7417545,1 +v1annealC_merge3_116k_120k,include_base_44_greek_medical_license,0,lm-eval,vllm,,acc,none,0.5671641791044776,0.042962562216652206,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ec8333914_2026-10-07T16-03-13.062373.json,1791388830.7417545,1 +v1annealC_merge3_116k_120k,include_base_44_greek_professional_certification,0,lm-eval,vllm,,acc,none,0.5149253731343284,0.043336177843127044,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ec8333914_2026-10-07T16-03-13.062373.json,1791388830.7417545,1 +v1annealC_merge3_116k_120k,include_base_44_greek_social_science,0,lm-eval,vllm,,acc,none,0.5298507462686567,0.043278164192160934,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ec8333914_2026-10-07T16-03-13.062373.json,1791388830.7417545,1 +v1annealC_merge3_116k_120k,include_base_44_greek_stem,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ec8333914_2026-10-07T16-03-13.062373.json,1791388830.7417545,1 +v1annealC_merge3_116k_120k,include_base_44_hungarian,0,lm-eval,vllm,yes,acc,none,0.4890909090909091,0.021370781188129927,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8d578977f6_2026-10-07T16-05-07.991066.json,1791388942.2591472,1 +v1annealC_merge3_116k_120k,include_base_44_hungarian_applied_science,0,lm-eval,vllm,,acc,none,0.4838709677419355,0.027102195174735676,341,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8d578977f6_2026-10-07T16-05-07.991066.json,1791388942.2591472,1 +v1annealC_merge3_116k_120k,include_base_44_hungarian_social_science,0,lm-eval,vllm,,acc,none,0.5,0.03696106354772864,184,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8d578977f6_2026-10-07T16-05-07.991066.json,1791388942.2591472,1 +v1annealC_merge3_116k_120k,include_base_44_hungarian_stem,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8d578977f6_2026-10-07T16-05-07.991066.json,1791388942.2591472,1 +v1annealC_merge3_116k_120k,include_base_44_italian,0,lm-eval,vllm,yes,acc,none,0.6678832116788321,0.019916199253263437,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5c48bf582_2026-10-07T15-47-10.435059.json,1791387857.2451358,1 +v1annealC_merge3_116k_120k,include_base_44_italian_applied_science,0,lm-eval,vllm,,acc,none,0.6571428571428571,0.08140424227436864,35,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5c48bf582_2026-10-07T15-47-10.435059.json,1791387857.2451358,1 +v1annealC_merge3_116k_120k,include_base_44_italian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6047904191616766,0.03794566248621298,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5c48bf582_2026-10-07T15-47-10.435059.json,1791387857.2451358,1 +v1annealC_merge3_116k_120k,include_base_44_italian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.8333333333333334,0.11236664374387369,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5c48bf582_2026-10-07T15-47-10.435059.json,1791387857.2451358,1 +v1annealC_merge3_116k_120k,include_base_44_italian_professional_certification,0,lm-eval,vllm,,acc,none,0.6193548387096774,0.039126370560334245,155,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5c48bf582_2026-10-07T15-47-10.435059.json,1791387857.2451358,1 +v1annealC_merge3_116k_120k,include_base_44_italian_social_science,0,lm-eval,vllm,,acc,none,0.7784431137724551,0.03223309610157502,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5c48bf582_2026-10-07T15-47-10.435059.json,1791387857.2451358,1 +v1annealC_merge3_116k_120k,include_base_44_italian_stem,0,lm-eval,vllm,,acc,none,0.5,0.15075567228888181,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5c48bf582_2026-10-07T15-47-10.435059.json,1791387857.2451358,1 +v1annealC_merge3_116k_120k,include_base_44_lithuanian,0,lm-eval,vllm,yes,acc,none,0.6048689138576779,0.021105697233309677,534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b4894a53c_2026-10-07T15-47-02.219437.json,1791387860.8857017,1 +v1annealC_merge3_116k_120k,include_base_44_lithuanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6059701492537314,0.026737262761200947,335,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b4894a53c_2026-10-07T15-47-02.219437.json,1791387860.8857017,1 +v1annealC_merge3_116k_120k,include_base_44_lithuanian_business_commerce,0,lm-eval,vllm,,acc,none,0.425,0.07915823166939519,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b4894a53c_2026-10-07T15-47-02.219437.json,1791387860.8857017,1 +v1annealC_merge3_116k_120k,include_base_44_lithuanian_professional_certification,0,lm-eval,vllm,,acc,none,0.6041666666666666,0.0713322023838232,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b4894a53c_2026-10-07T15-47-02.219437.json,1791387860.8857017,1 +v1annealC_merge3_116k_120k,include_base_44_lithuanian_social_science,0,lm-eval,vllm,,acc,none,0.6493506493506493,0.05473553444308601,77,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b4894a53c_2026-10-07T15-47-02.219437.json,1791387860.8857017,1 +v1annealC_merge3_116k_120k,include_base_44_lithuanian_stem,0,lm-eval,vllm,,acc,none,0.7058823529411765,0.07931763087802848,34,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b4894a53c_2026-10-07T15-47-02.219437.json,1791387860.8857017,1 +v1annealC_merge3_116k_120k,include_base_44_north macedonian,0,lm-eval,vllm,yes,acc,none,0.7894736842105263,0.017348975111082795,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/86489114fa_2026-10-07T16-03-12.069163.json,1791388831.527541,1 +v1annealC_merge3_116k_120k,include_base_44_north macedonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.8169642857142857,0.025895066065843634,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/86489114fa_2026-10-07T16-03-12.069163.json,1791388831.527541,1 +v1annealC_merge3_116k_120k,include_base_44_north macedonian_business_commerce,0,lm-eval,vllm,,acc,none,0.7678571428571429,0.028272580246830843,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/86489114fa_2026-10-07T16-03-12.069163.json,1791388831.527541,1 +v1annealC_merge3_116k_120k,include_base_44_north macedonian_social_science,0,lm-eval,vllm,,acc,none,0.8490566037735849,0.0496447935456809,53,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/86489114fa_2026-10-07T16-03-12.069163.json,1791388831.527541,1 +v1annealC_merge3_116k_120k,include_base_44_north macedonian_stem,0,lm-eval,vllm,,acc,none,0.7,0.06546536707079771,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/86489114fa_2026-10-07T16-03-12.069163.json,1791388831.527541,1 +v1annealC_merge3_116k_120k,include_base_44_polish,0,lm-eval,vllm,yes,acc,none,0.5237226277372263,0.021104850110738725,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/713ef3ad88_2026-10-07T16-05-07.794360.json,1791388947.4455938,1 +v1annealC_merge3_116k_120k,include_base_44_polish_professional_certification,0,lm-eval,vllm,,acc,none,0.5423387096774194,0.022392613936627653,496,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/713ef3ad88_2026-10-07T16-05-07.794360.json,1791388947.4455938,1 +v1annealC_merge3_116k_120k,include_base_44_polish_social_science,0,lm-eval,vllm,,acc,none,1.0,0.0,4,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/713ef3ad88_2026-10-07T16-05-07.794360.json,1791388947.4455938,1 +v1annealC_merge3_116k_120k,include_base_44_polish_stem,0,lm-eval,vllm,,acc,none,0.2916666666666667,0.06629996666059658,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/713ef3ad88_2026-10-07T16-05-07.794360.json,1791388947.4455938,1 +v1annealC_merge3_116k_120k,include_base_44_portuguese,0,lm-eval,vllm,yes,acc,none,0.5807622504537205,0.020942128427434713,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d285831222_2026-10-07T16-03-21.783020.json,1791388834.967445,1 +v1annealC_merge3_116k_120k,include_base_44_portuguese_applied_science,0,lm-eval,vllm,,acc,none,0.5,0.05488212999484517,84,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d285831222_2026-10-07T16-03-21.783020.json,1791388834.967445,1 +v1annealC_merge3_116k_120k,include_base_44_portuguese_arts_humanities,0,lm-eval,vllm,,acc,none,0.6038961038961039,0.039540299587534244,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d285831222_2026-10-07T16-03-21.783020.json,1791388834.967445,1 +v1annealC_merge3_116k_120k,include_base_44_portuguese_business_commerce,0,lm-eval,vllm,,acc,none,0.4722222222222222,0.05924743948371487,72,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d285831222_2026-10-07T16-03-21.783020.json,1791388834.967445,1 +v1annealC_merge3_116k_120k,include_base_44_portuguese_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5967741935483871,0.06280789804452513,62,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d285831222_2026-10-07T16-03-21.783020.json,1791388834.967445,1 +v1annealC_merge3_116k_120k,include_base_44_portuguese_social_science,0,lm-eval,vllm,,acc,none,0.6558441558441559,0.03840892794235726,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d285831222_2026-10-07T16-03-21.783020.json,1791388834.967445,1 +v1annealC_merge3_116k_120k,include_base_44_portuguese_stem,0,lm-eval,vllm,,acc,none,0.52,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d285831222_2026-10-07T16-03-21.783020.json,1791388834.967445,1 +v1annealC_merge3_116k_120k,include_base_44_serbian,0,lm-eval,vllm,yes,acc,none,0.6818181818181818,0.01968243679803424,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d3bb8e4b1a_2026-10-07T16-23-37.272653.json,1791390052.7559593,1 +v1annealC_merge3_116k_120k,include_base_44_serbian_arts_humanities,0,lm-eval,vllm,,acc,none,0.65814696485623,0.026853683406968108,313,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d3bb8e4b1a_2026-10-07T16-23-37.272653.json,1791390052.7559593,1 +v1annealC_merge3_116k_120k,include_base_44_serbian_social_science,0,lm-eval,vllm,,acc,none,0.7647058823529411,0.03110257015343263,187,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d3bb8e4b1a_2026-10-07T16-23-37.272653.json,1791390052.7559593,1 +v1annealC_merge3_116k_120k,include_base_44_serbian_stem,0,lm-eval,vllm,,acc,none,0.52,0.0713714056959817,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d3bb8e4b1a_2026-10-07T16-23-37.272653.json,1791390052.7559593,1 +v1annealC_merge3_116k_120k,include_base_44_spanish,0,lm-eval,vllm,yes,acc,none,0.6163636363636363,0.020328307682640316,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a17b5350dc_2026-10-07T15-48-54.367345.json,1791387965.9466136,1 +v1annealC_merge3_116k_120k,include_base_44_spanish_arts_humanities,0,lm-eval,vllm,,acc,none,0.504,0.0316851985511992,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a17b5350dc_2026-10-07T15-48-54.367345.json,1791387965.9466136,1 +v1annealC_merge3_116k_120k,include_base_44_spanish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a17b5350dc_2026-10-07T15-48-54.367345.json,1791387965.9466136,1 +v1annealC_merge3_116k_120k,include_base_44_spanish_social_science,0,lm-eval,vllm,,acc,none,0.72,0.02845414827783231,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a17b5350dc_2026-10-07T15-48-54.367345.json,1791387965.9466136,1 +v1annealC_merge3_116k_120k,include_base_44_spanish_stem,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a17b5350dc_2026-10-07T15-48-54.367345.json,1791387965.9466136,1 +v1annealC_merge3_116k_120k,include_base_44_turkish,0,lm-eval,vllm,yes,acc,none,0.5456204379562044,0.020945529304505852,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/948ca30912_2026-10-07T15-47-05.695904.json,1791387865.1708786,1 +v1annealC_merge3_116k_120k,include_base_44_turkish_arts_humanities,0,lm-eval,vllm,,acc,none,0.5542168674698795,0.03869543323472097,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/948ca30912_2026-10-07T15-47-05.695904.json,1791387865.1708786,1 +v1annealC_merge3_116k_120k,include_base_44_turkish_business_commerce,0,lm-eval,vllm,,acc,none,0.6626506024096386,0.03680783690727582,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/948ca30912_2026-10-07T15-47-05.695904.json,1791387865.1708786,1 +v1annealC_merge3_116k_120k,include_base_44_turkish_social_science,0,lm-eval,vllm,,acc,none,0.4819277108433735,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/948ca30912_2026-10-07T15-47-05.695904.json,1791387865.1708786,1 +v1annealC_merge3_116k_120k,include_base_44_turkish_stem,0,lm-eval,vllm,,acc,none,0.34,0.0676726816132972,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/948ca30912_2026-10-07T15-47-05.695904.json,1791387865.1708786,1 +v1annealC_merge3_116k_120k,include_base_44_ukrainian,0,lm-eval,vllm,yes,acc,none,0.6163636363636363,0.020773476140316566,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/21810e74ad_2026-10-07T15-53-01.038276.json,1791388218.4049788,1 +v1annealC_merge3_116k_120k,include_base_44_ukrainian_arts_humanities,0,lm-eval,vllm,,acc,none,0.632,0.03056207062099311,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/21810e74ad_2026-10-07T15-53-01.038276.json,1791388218.4049788,1 +v1annealC_merge3_116k_120k,include_base_44_ukrainian_social_science,0,lm-eval,vllm,,acc,none,0.612,0.030881038748993974,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/21810e74ad_2026-10-07T15-53-01.038276.json,1791388218.4049788,1 +v1annealC_merge3_116k_120k,include_base_44_ukrainian_stem,0,lm-eval,vllm,,acc,none,0.56,0.07091242083423346,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/21810e74ad_2026-10-07T15-53-01.038276.json,1791388218.4049788,1 +v1annealC_merge3_116k_120k,jeopardy,10,lm-eval,vllm,,exact_match,strict-match,0.5148795465281059,0.010864751088152947,2117,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4535133206_2026-10-07T16-05-56.498927.json,1791388946.3185377,1 +v1annealC_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,acc,none,0.7056083834659421,0.006349750457397468,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fb441f842c_2026-10-07T16-28-03.624124.json,1791390297.2550402,1 +v1annealC_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,perplexity,none,4.0752241256896715,0.08726612087593784,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fb441f842c_2026-10-07T16-28-03.624124.json,1791390297.2550402,1 +v1annealC_merge3_116k_120k,mbpp,3,lm-eval,vllm,,pass_at_1,none,0.52,0.022365160424231333,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b6dfc005b_2026-10-07T16-24-13.269795.json,1791390054.4780123,1 +v1annealC_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.56,0.03145724452223565,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3cf79d34df_2026-10-07T16-03-29.722681.json,1791388834.9096246,1 +v1annealC_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,strict-match,0.652,0.03018656846451169,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3cf79d34df_2026-10-07T16-03-29.722681.json,1791388834.9096246,1 +v1annealC_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.684,0.029462657598578676,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/97cd6c3249_2026-10-07T15-47-16.045986.json,1791387863.6583257,1 +v1annealC_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,strict-match,0.604,0.030993197854577843,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/97cd6c3249_2026-10-07T15-47-16.045986.json,1791387863.6583257,1 +v1annealC_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.668,0.029844039047465888,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aefd45d6ee_2026-10-07T16-03-18.104186.json,1791388829.599847,1 +v1annealC_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,strict-match,0.572,0.03135596892377262,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aefd45d6ee_2026-10-07T16-03-18.104186.json,1791388829.599847,1 +v1annealC_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.52,0.031660853408495185,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f26b25ccf_2026-10-07T16-05-31.569355.json,1791388956.460694,1 +v1annealC_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,strict-match,0.628,0.030630325944558313,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f26b25ccf_2026-10-07T16-05-31.569355.json,1791388956.460694,1 +v1annealC_merge3_116k_120k,mmlu,5,lm-eval,vllm,yes,acc,none,0.6684233015239994,0.0037523626036826134,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_abstract_algebra,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_anatomy,5,lm-eval,vllm,,acc,none,0.5777777777777777,0.042667634040995855,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_astronomy,5,lm-eval,vllm,,acc,none,0.7302631578947368,0.036117805602848975,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7283018867924528,0.027377706624670702,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_college_biology,5,lm-eval,vllm,,acc,none,0.8125,0.032639560491693344,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_college_mathematics,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_college_medicine,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.03414014007044037,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_computer_security,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_conceptual_physics,5,lm-eval,vllm,,acc,none,0.723404255319149,0.0292418838696288,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_econometrics,5,lm-eval,vllm,,acc,none,0.5,0.047036043419179864,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6275862068965518,0.0402873153294756,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.46296296296296297,0.025680564640056906,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6009852216748769,0.03445487686264716,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_geography,5,lm-eval,vllm,,acc,none,0.8383838383838383,0.02622591986362927,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9119170984455959,0.020453746601601056,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7512820512820513,0.021916957709213813,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.3851851851851852,0.029670906124630803,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8319327731092437,0.024289102115692317,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_physics,5,lm-eval,vllm,,acc,none,0.5165562913907285,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8587155963302753,0.014933868987028072,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6157407407407407,0.03317354514310747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8088235294117647,0.02759917430064072,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8227848101265823,0.024856364184503203,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_human_aging,5,lm-eval,vllm,,acc,none,0.7399103139013453,0.029442495585857424,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_human_sexuality,5,lm-eval,vllm,,acc,none,0.8091603053435115,0.03446513350752599,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_humanities,5,lm-eval,vllm,yes,acc,none,0.6131774707757705,0.006673959600679044,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_jurisprudence,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.04019107472557348,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7852760736196319,0.032262193772867716,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_machine_learning,5,lm-eval,vllm,,acc,none,0.44642857142857145,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_management,5,lm-eval,vllm,,acc,none,0.7766990291262136,0.041235531898914324,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_marketing,5,lm-eval,vllm,,acc,none,0.9188034188034188,0.017893784904018484,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_medical_genetics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_miscellaneous,5,lm-eval,vllm,,acc,none,0.7816091954022989,0.014774358319934516,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_moral_disputes,5,lm-eval,vllm,,acc,none,0.7398843930635838,0.02361867831006933,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3642458100558659,0.016094338768474478,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_nutrition,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.024848018263875137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_other,5,lm-eval,vllm,yes,acc,none,0.7080785323463148,0.007890591635357885,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_philosophy,5,lm-eval,vllm,,acc,none,0.7717041800643086,0.023839303311398267,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_prehistory,5,lm-eval,vllm,,acc,none,0.7623456790123457,0.023683591837008515,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_professional_accounting,5,lm-eval,vllm,,acc,none,0.5,0.029827499313594685,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_professional_law,5,lm-eval,vllm,,acc,none,0.5208604954367666,0.012759117066518041,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_professional_medicine,5,lm-eval,vllm,,acc,none,0.6433823529411765,0.029097209568412025,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_professional_psychology,5,lm-eval,vllm,,acc,none,0.7075163398692811,0.01840341571010967,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7848553786155346,0.007252027887423541,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_sociology,5,lm-eval,vllm,,acc,none,0.845771144278607,0.025538433368578303,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_stem,5,lm-eval,vllm,yes,acc,none,0.5981604820805582,0.008339449575537925,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_virology,5,lm-eval,vllm,,acc,none,0.5301204819277109,0.03885425420866771,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,mmlu_world_religions,5,lm-eval,vllm,,acc,none,0.783625730994152,0.03158149539338735,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/400950b065_2026-10-07T16-22-28.264005.json,1791389804.4845939,1 +v1annealC_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc,none,0.9808787632221319,0.0027628867099281857,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/07117656fe_2026-10-07T16-23-38.631317.json,1791390049.4699368,1 +v1annealC_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc_norm,none,0.9751830756712775,0.0031384446785371408,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/07117656fe_2026-10-07T16-23-38.631317.json,1791390049.4699368,1 +v1annealC_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc,none,0.9746059544658494,0.0032925131749552126,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b114bdbaa8_2026-10-07T15-38-38.784449.json,1791387348.7887332,1 +v1annealC_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc_norm,none,0.9741681260945709,0.0033200296187351425,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b114bdbaa8_2026-10-07T15-38-38.784449.json,1791387348.7887332,1 +v1annealC_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc,none,0.9532424812030075,0.0032365151223192976,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a9f7cbc1f_2026-10-07T16-24-00.615185.json,1791390053.2217085,1 +v1annealC_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc_norm,none,0.9555921052631579,0.003158032439480209,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a9f7cbc1f_2026-10-07T16-24-00.615185.json,1791390053.2217085,1 +v1annealC_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/366e165f34_2026-10-07T16-04-44.450141.json,1791388948.2036662,1 +v1annealC_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/366e165f34_2026-10-07T16-04-44.450141.json,1791388948.2036662,1 +v1annealC_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc,none,0.9769364664926022,0.003131955519540886,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e5068b565b_2026-10-07T15-53-06.827962.json,1791388223.3388581,1 +v1annealC_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc_norm,none,0.9751958224543081,0.0032450981299286183,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e5068b565b_2026-10-07T15-53-06.827962.json,1791388223.3388581,1 +v1annealC_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc,none,0.9936131386861314,0.0024073838689802887,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d736162a82_2026-10-07T16-15-19.664726.json,1791389565.5924044,1 +v1annealC_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc_norm,none,0.9908759124087592,0.0028734080153557592,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d736162a82_2026-10-07T16-15-19.664726.json,1791389565.5924044,1 +v1annealC_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc,none,0.9883116883116884,0.0038757850932000515,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b9543eb73e_2026-10-07T16-21-13.408025.json,1791389928.4859195,1 +v1annealC_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc_norm,none,0.9844155844155844,0.004466541060441909,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b9543eb73e_2026-10-07T16-21-13.408025.json,1791389928.4859195,1 +v1annealC_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc,none,0.9207766990291262,0.00532352571250615,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6ccf072f08_2026-10-07T16-15-34.082223.json,1791389565.4009733,1 +v1annealC_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc_norm,none,0.9168932038834952,0.005440932969230756,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6ccf072f08_2026-10-07T16-15-34.082223.json,1791389565.4009733,1 +v1annealC_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc,none,0.967032967032967,0.010826201825755803,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/491a0ea86d_2026-10-07T16-21-13.278059.json,1791389930.0164766,1 +v1annealC_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc_norm,none,0.6556776556776557,0.02881000563547052,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/491a0ea86d_2026-10-07T16-21-13.278059.json,1791389930.0164766,1 +v1annealC_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc,none,0.9517509727626459,0.0042278920836052985,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc3d52e8cf_2026-10-07T16-01-15.101623.json,1791388710.1068103,1 +v1annealC_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc_norm,none,0.9431906614785992,0.004566963705208012,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc3d52e8cf_2026-10-07T16-01-15.101623.json,1791388710.1068103,1 +v1annealC_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc,none,0.9866562009419152,0.0022735693141618706,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/741cf90d3f_2026-10-07T15-47-10.649840.json,1791387859.1498818,1 +v1annealC_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc_norm,none,0.9815541601255887,0.0026661948099714764,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/741cf90d3f_2026-10-07T15-47-10.649840.json,1791387859.1498818,1 +v1annealC_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc,none,0.9285714285714286,0.04956347617776506,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/07f4d9bdcc_2026-10-07T16-23-05.592952.json,1791390050.5088205,1 +v1annealC_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc_norm,none,0.8214285714285714,0.07370704611510599,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/07f4d9bdcc_2026-10-07T16-23-05.592952.json,1791390050.5088205,1 +v1annealC_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc,none,0.9694555112881806,0.006275111565630337,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4727794885_2026-10-07T16-20-36.594035.json,1791389891.1309662,1 +v1annealC_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc_norm,none,0.952191235059761,0.007780489692849838,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4727794885_2026-10-07T16-20-36.594035.json,1791389891.1309662,1 +v1annealC_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc,none,0.9799147900182593,0.0024477364638721393,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bc4bd87a71_2026-10-07T16-05-30.553554.json,1791388949.759574,1 +v1annealC_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc_norm,none,0.9799147900182593,0.0024477364638721393,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bc4bd87a71_2026-10-07T16-05-30.553554.json,1791388949.759574,1 +v1annealC_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc,none,0.9834319526627219,0.004393762697892139,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98055ea6d3_2026-10-07T15-48-42.131144.json,1791387965.3329446,1 +v1annealC_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc_norm,none,0.9798816568047337,0.004832943264222541,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98055ea6d3_2026-10-07T15-48-42.131144.json,1791387965.3329446,1 +v1annealC_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc,none,0.9814352017136737,0.002550920460687694,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/30e08a2f0e_2026-10-07T16-23-48.754910.json,1791390050.6463225,1 +v1annealC_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc_norm,none,0.9739378793288112,0.003010866423551133,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/30e08a2f0e_2026-10-07T16-23-48.754910.json,1791390050.6463225,1 +v1annealC_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc,none,0.9649883294431477,0.003357002254489563,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72e2452129_2026-10-07T15-51-14.485472.json,1791388090.8479006,1 +v1annealC_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc_norm,none,0.9533177725908636,0.003852820850159222,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72e2452129_2026-10-07T15-51-14.485472.json,1791388090.8479006,1 +v1annealC_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc,none,0.8872549019607843,0.022198571039456782,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fc845792_2026-10-07T16-21-25.337983.json,1791389930.4914846,1 +v1annealC_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc_norm,none,0.7843137254901961,0.028867431449849337,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fc845792_2026-10-07T16-21-25.337983.json,1791389930.4914846,1 +v1annealC_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc,none,0.945580474934037,0.00412034568341389,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03885ca7e0_2026-10-07T16-01-35.604952.json,1791388702.480603,1 +v1annealC_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc_norm,none,0.941622691292876,0.0042586066146874345,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/03885ca7e0_2026-10-07T16-01-35.604952.json,1791388702.480603,1 +v1annealC_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc,none,0.9830508474576272,0.0037592835351431242,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bd2fb43da4_2026-10-07T16-19-22.662999.json,1791389804.4100058,1 +v1annealC_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc_norm,none,0.976271186440678,0.0044326796440137374,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bd2fb43da4_2026-10-07T16-19-22.662999.json,1791389804.4100058,1 +v1annealC_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/49c5820b26_2026-10-07T16-04-41.647369.json,1791388947.8763707,1 +v1annealC_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/49c5820b26_2026-10-07T16-04-41.647369.json,1791388947.8763707,1 +v1annealC_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc,none,0.9480909480909481,0.004595879019862996,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fb3aa9f478_2026-10-07T16-21-31.752814.json,1791389924.80023,1 +v1annealC_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc_norm,none,0.9232089232089232,0.005516040103102192,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fb3aa9f478_2026-10-07T16-21-31.752814.json,1791389924.80023,1 +v1annealC_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc,none,0.9633251833740831,0.003286473693804805,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/de2c0a9d5e_2026-10-07T16-03-19.743887.json,1791388831.2440593,1 +v1annealC_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc_norm,none,0.9382640586797066,0.004208150905987891,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/de2c0a9d5e_2026-10-07T16-03-19.743887.json,1791388831.2440593,1 +v1annealC_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc,none,0.9714566929133859,0.00301666885983574,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5cc5d5cf87_2026-10-07T16-19-41.132402.json,1791389804.7661977,1 +v1annealC_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc_norm,none,0.9681758530183727,0.0031799426098298245,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5cc5d5cf87_2026-10-07T16-19-41.132402.json,1791389804.7661977,1 +v1annealC_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc,none,0.9698443579766537,0.0037725013017597645,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f56acf421f_2026-10-07T15-47-05.287171.json,1791387857.4191113,1 +v1annealC_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc_norm,none,0.9615758754863813,0.004240214793311917,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f56acf421f_2026-10-07T15-47-05.287171.json,1791387857.4191113,1 +v1annealC_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc,none,0.9392038600723763,0.003712000824361302,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/91a27c0acc_2026-10-07T15-38-45.158723.json,1791387349.378392,1 +v1annealC_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc_norm,none,0.9478890229191798,0.0034524983661499355,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/91a27c0acc_2026-10-07T15-38-45.158723.json,1791387349.378392,1 +v1annealC_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc,none,0.9357573053758643,0.0036623307334960236,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f5ddd98d6_2026-10-07T15-39-10.503641.json,1791387352.7489696,1 +v1annealC_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc_norm,none,0.9250501896051752,0.0039330728567521425,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f5ddd98d6_2026-10-07T15-39-10.503641.json,1791387352.7489696,1 +v1annealC_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc,none,0.9763872491145218,0.0030127804460631574,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/509bd2df1a_2026-10-07T16-05-27.797581.json,1791388942.8162324,1 +v1annealC_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc_norm,none,0.9775678866587958,0.00293826999506148,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/509bd2df1a_2026-10-07T16-05-27.797581.json,1791388942.8162324,1 +v1annealC_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc,none,0.9629629629629629,0.012139903284390536,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/23aff3cead_2026-10-07T15-38-18.370314.json,1791387355.353855,1 +v1annealC_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc_norm,none,0.9423868312757202,0.0149784820195792,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/23aff3cead_2026-10-07T15-38-18.370314.json,1791387355.353855,1 +v1annealC_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc,none,1.0,0.0,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aa172b78b0_2026-10-07T16-02-51.279069.json,1791388833.4924588,1 +v1annealC_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc_norm,none,0.9950248756218906,0.004975124378109453,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aa172b78b0_2026-10-07T16-02-51.279069.json,1791388833.4924588,1 +v1annealC_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc,none,0.9236509758897818,0.00636438298951598,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/28a7d3c755_2026-10-07T16-21-25.902182.json,1791389929.1555135,1 +v1annealC_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc_norm,none,0.8547646383467279,0.008444230375772814,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/28a7d3c755_2026-10-07T16-21-25.902182.json,1791389929.1555135,1 +v1annealC_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc,none,0.9737609329446064,0.0030520206257348753,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38c60b0d0d_2026-10-07T15-51-05.744336.json,1791388089.9099162,1 +v1annealC_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc_norm,none,0.967201166180758,0.0034007499719348557,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38c60b0d0d_2026-10-07T15-51-05.744336.json,1791388089.9099162,1 +v1annealC_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc,none,0.328,0.021017027165175464,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b0fd9fa573_2026-10-07T16-03-21.959515.json,1791388832.4263983,1 +v1annealC_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc_norm,none,0.452,0.022279694107843542,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b0fd9fa573_2026-10-07T16-03-21.959515.json,1791388832.4263983,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,bleu,none,15.487553193396772,0.2720164895968928,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7aad15e6a5_2026-10-07T15-54-56.296680.json,1791388218.939308,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,chrf,none,32.68113899797742,0.32819901005699775,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7aad15e6a5_2026-10-07T15-54-56.296680.json,1791388218.939308,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,bleu,none,18.63444988936438,0.26202805531936496,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7c40d8840e_2026-10-07T16-23-37.294687.json,1791389928.3874128,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,chrf,none,35.6949468594632,0.27854302289986826,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7c40d8840e_2026-10-07T16-23-37.294687.json,1791389928.3874128,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,bleu,none,29.50056726921148,0.33280197101985726,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/39842cb906_2026-10-07T15-40-24.308793.json,1791387347.295616,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,chrf,none,48.77551910548924,0.27199303382725404,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/39842cb906_2026-10-07T15-40-24.308793.json,1791387347.295616,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,bleu,none,27.22917377747753,0.3136302982597335,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e1c7cf6ee2_2026-10-07T15-49-13.125117.json,1791387853.3503397,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,chrf,none,47.97290048440359,0.2642104022287405,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e1c7cf6ee2_2026-10-07T15-49-13.125117.json,1791387853.3503397,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,bleu,none,26.184643494093482,0.3531062945082515,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aab07e06af_2026-10-07T15-55-05.020419.json,1791388218.501833,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,chrf,none,42.93570998241011,0.41182248722403225,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aab07e06af_2026-10-07T15-55-05.020419.json,1791388218.501833,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,bleu,none,13.521189272385616,0.23258200122186146,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9850184f60_2026-10-07T15-51-20.870637.json,1791387966.2420275,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,chrf,none,39.98477239247143,0.24219640213293364,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9850184f60_2026-10-07T15-51-20.870637.json,1791387966.2420275,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,bleu,none,17.669396258021774,0.30950927005408035,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2574cf8892_2026-10-07T15-55-04.232888.json,1791388218.626697,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,chrf,none,40.51177614629025,0.24914641001351218,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2574cf8892_2026-10-07T15-55-04.232888.json,1791388218.626697,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,bleu,none,29.266755445963643,0.3097485202456013,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b094408da1_2026-10-07T16-23-52.502196.json,1791389934.5945108,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,chrf,none,51.81624886271403,0.20950275459699239,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b094408da1_2026-10-07T16-23-52.502196.json,1791389934.5945108,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,bleu,none,23.056143185421597,0.31538251498182557,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b526dafd2_2026-10-07T16-19-40.432562.json,1791389690.6178632,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,chrf,none,48.64287626406289,0.2665637936450449,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b526dafd2_2026-10-07T16-19-40.432562.json,1791389690.6178632,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,bleu,none,24.422591419190425,0.3201127594020198,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/623a3ed039_2026-10-07T16-05-39.464523.json,1791388835.427389,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,chrf,none,48.949512671746,0.28273180579616486,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/623a3ed039_2026-10-07T16-05-39.464523.json,1791388835.427389,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,bleu,none,28.75602182633771,0.31476089654974315,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3ba7dc0ca_2026-10-07T15-55-13.568309.json,1791388217.1569612,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,chrf,none,52.18671149034849,0.28016099836270464,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3ba7dc0ca_2026-10-07T15-55-13.568309.json,1791388217.1569612,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,bleu,none,21.770743029897456,0.3678007158540292,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/054124bb4a_2026-10-07T16-07-07.934304.json,1791388941.4448206,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,chrf,none,46.83453737886682,0.2648925155214113,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/054124bb4a_2026-10-07T16-07-07.934304.json,1791388941.4448206,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,bleu,none,17.39504199325007,0.3186235918571813,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/91df9a885c_2026-10-07T16-17-26.192330.json,1791389561.9710162,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,chrf,none,47.48885675726536,0.23741136034802698,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/91df9a885c_2026-10-07T16-17-26.192330.json,1791389561.9710162,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,bleu,none,16.215125164945114,0.24093107579389555,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b7e514a781_2026-10-07T15-50-47.418231.json,1791387960.8357153,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,chrf,none,43.91616594847708,0.25425268436837106,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b7e514a781_2026-10-07T15-50-47.418231.json,1791387960.8357153,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,bleu,none,25.29148022232238,0.3355965436645605,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/638584dad3_2026-10-07T16-17-33.313952.json,1791389561.970394,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,chrf,none,52.80408397302971,0.2725287467277775,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/638584dad3_2026-10-07T16-17-33.313952.json,1791389561.970394,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,bleu,none,16.598755504759872,0.25624776394548543,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e263cb0b0e_2026-10-07T16-07-22.626703.json,1791388955.8109322,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,chrf,none,40.42133649124156,0.2459468050148744,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e263cb0b0e_2026-10-07T16-07-22.626703.json,1791388955.8109322,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,bleu,none,27.892409493036766,0.40751914153347196,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9b428e949_2026-10-07T15-53-25.035572.json,1791388090.8795428,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,chrf,none,51.85268293618742,0.2506744751011558,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9b428e949_2026-10-07T15-53-25.035572.json,1791388090.8795428,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,bleu,none,18.139260209688757,0.2934678227453881,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/97b0c2018e_2026-10-07T16-05-14.871224.json,1791388834.3181336,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,chrf,none,43.15192824138661,0.2586300549069307,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/97b0c2018e_2026-10-07T16-05-14.871224.json,1791388834.3181336,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,bleu,none,20.388012390141476,0.33603095965625635,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c01d4a265c_2026-10-07T16-29-55.986610.json,1791390291.8082528,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,chrf,none,44.62242224859709,0.25258510967814557,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c01d4a265c_2026-10-07T16-29-55.986610.json,1791390291.8082528,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,bleu,none,19.898499626251006,0.27161363067505256,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dda2257d3b_2026-10-07T16-07-22.819226.json,1791388949.7369668,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,chrf,none,46.584776505061555,0.24924835278370935,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dda2257d3b_2026-10-07T16-07-22.819226.json,1791388949.7369668,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,bleu,none,31.281027098217596,0.3220015302296119,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/59f5d55ac6_2026-10-07T15-49-02.285080.json,1791387861.3562021,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,chrf,none,55.380745464098844,0.2667139222720629,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/59f5d55ac6_2026-10-07T15-49-02.285080.json,1791387861.3562021,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,bleu,none,20.52803689949964,0.3106624501622796,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/28ae6f082b_2026-10-07T16-19-57.661992.json,1791389692.213183,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,chrf,none,45.87014112363102,0.2562904087838819,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/28ae6f082b_2026-10-07T16-19-57.661992.json,1791389692.213183,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,bleu,none,24.27224226878836,0.3089310677888776,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9423271023_2026-10-07T15-40-57.521976.json,1791387355.3465762,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,chrf,none,50.88708271330012,0.27080874155521517,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9423271023_2026-10-07T15-40-57.521976.json,1791387355.3465762,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,bleu,none,26.08535749631062,0.3673989938741904,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f543d5b676_2026-10-07T16-07-13.468824.json,1791388942.1705015,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,chrf,none,51.34970613060285,0.2854214000245577,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f543d5b676_2026-10-07T16-07-13.468824.json,1791388942.1705015,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,bleu,none,24.528104410225524,0.36619586148306466,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/92499c15b2_2026-10-07T16-30-03.472852.json,1791390300.0192223,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,chrf,none,47.58023600913954,0.27340449455826665,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/92499c15b2_2026-10-07T16-30-03.472852.json,1791390300.0192223,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,bleu,none,16.290541594808253,0.25576354198621265,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0195071915_2026-10-07T15-44-34.703324.json,1791387599.7221644,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,chrf,none,42.810826552937556,0.22492001695477262,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0195071915_2026-10-07T15-44-34.703324.json,1791387599.7221644,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,bleu,none,7.049771605375517,0.22964913681537297,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a6e5a4b621_2026-10-07T15-49-08.039140.json,1791387859.5217063,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,chrf,none,12.39966082315087,0.34760166670034676,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a6e5a4b621_2026-10-07T15-49-08.039140.json,1791387859.5217063,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,bleu,none,33.84941615258034,0.3438007536367511,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b4f9186c5b_2026-10-07T16-05-17.411398.json,1791388827.0593557,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,chrf,none,55.20659458652858,0.2721753276276294,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b4f9186c5b_2026-10-07T16-05-17.411398.json,1791388827.0593557,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,bleu,none,19.57516221192201,0.3288556564066766,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8e4cc12457_2026-10-07T16-25-34.459876.json,1791390044.6884353,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,chrf,none,48.194957276393325,0.27782041300773264,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8e4cc12457_2026-10-07T16-25-34.459876.json,1791390044.6884353,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,bleu,none,16.49034698734813,0.2572875602676423,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e8e185d35e_2026-10-07T16-29-53.510167.json,1791390295.9850125,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,chrf,none,38.71798206649329,0.25608341009659,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e8e185d35e_2026-10-07T16-29-53.510167.json,1791390295.9850125,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,bleu,none,31.015626138434943,0.3159065164244304,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e25e263420_2026-10-07T15-53-01.740834.json,1791388091.4894795,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,chrf,none,50.190187173390555,0.27391159412251365,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e25e263420_2026-10-07T15-53-01.740834.json,1791388091.4894795,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,bleu,none,27.391445754147384,0.3221827601137443,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ecc377ccb_2026-10-07T16-21-46.500964.json,1791389810.1259582,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,chrf,none,46.039388572708255,0.26073296202863716,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ecc377ccb_2026-10-07T16-21-46.500964.json,1791389810.1259582,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,bleu,none,22.80662562268718,0.3246918713943011,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a2a14613cc_2026-10-07T15-53-08.201643.json,1791388095.6249244,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,chrf,none,42.869069894235736,0.2667943780769976,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a2a14613cc_2026-10-07T15-53-08.201643.json,1791388095.6249244,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,bleu,none,18.901360116556525,0.27438176789667806,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/88fc132586_2026-10-07T16-05-23.922116.json,1791388837.2262397,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,chrf,none,38.630693124303924,0.2527248952623644,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/88fc132586_2026-10-07T16-05-23.922116.json,1791388837.2262397,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,bleu,none,17.873648926952573,0.39279099036391935,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/52b11be068_2026-10-07T16-29-29.808800.json,1791390295.2646234,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,chrf,none,33.79262566541853,0.4017510260376883,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/52b11be068_2026-10-07T16-29-29.808800.json,1791390295.2646234,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,bleu,none,22.283607100725753,0.3002051147788332,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c8b73a5600_2026-10-07T16-21-28.173597.json,1791389804.482349,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,chrf,none,40.973352008530725,0.26151849679076694,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c8b73a5600_2026-10-07T16-21-28.173597.json,1791389804.482349,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,bleu,none,30.646774989870487,0.3002681162679449,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/14d3def422_2026-10-07T16-17-28.995587.json,1791389563.6063998,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,chrf,none,49.00175952053075,0.2590825818668753,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/14d3def422_2026-10-07T16-17-28.995587.json,1791389563.6063998,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,bleu,none,22.912333386209923,0.3314554893954873,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4fee7e6798_2026-10-07T15-50-49.203504.json,1791387966.7887614,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,chrf,none,40.08098865767998,0.29229163404390296,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4fee7e6798_2026-10-07T15-50-49.203504.json,1791387966.7887614,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,bleu,none,24.710150662297615,0.3205836266127004,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7f77e16c6e_2026-10-07T16-23-37.282046.json,1791389933.4295707,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,chrf,none,42.86870962131655,0.30587921369538296,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7f77e16c6e_2026-10-07T16-23-37.282046.json,1791389933.4295707,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,bleu,none,22.668694265631515,0.29660574177796906,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/902d686fc5_2026-10-07T16-29-28.176619.json,1791390288.9652884,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,chrf,none,42.14249354633034,0.2522284226494426,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/902d686fc5_2026-10-07T16-29-28.176619.json,1791390288.9652884,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,bleu,none,30.568970079780655,0.34299777167044393,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c5d5d1d497_2026-10-07T16-05-05.570961.json,1791388827.5850024,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,chrf,none,49.16838077315134,0.3166515517798367,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c5d5d1d497_2026-10-07T16-05-05.570961.json,1791388827.5850024,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,bleu,none,25.951550474044687,0.3101845197544579,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/11a021526b_2026-10-07T16-05-23.955640.json,1791388834.2441578,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,chrf,none,45.047111556596484,0.27314142566920796,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/11a021526b_2026-10-07T16-05-23.955640.json,1791388834.2441578,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,bleu,none,33.0516522916013,0.33238070974895084,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d9bf974a2_2026-10-07T15-53-08.544841.json,1791388098.7770154,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,chrf,none,51.75504528910386,0.2722102137301817,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d9bf974a2_2026-10-07T15-53-08.544841.json,1791388098.7770154,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,bleu,none,32.077028089057514,0.3883890499920128,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d753cd03e7_2026-10-07T15-54-56.619964.json,1791388221.8983512,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,chrf,none,49.97355792285021,0.3023589105941131,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d753cd03e7_2026-10-07T15-54-56.619964.json,1791388221.8983512,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,bleu,none,21.652870791625123,0.3320355380824775,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb00127b14_2026-10-07T15-54-56.233109.json,1791388218.242657,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,chrf,none,37.1111177583341,0.32317211462443957,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb00127b14_2026-10-07T15-54-56.233109.json,1791388218.242657,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,bleu,none,14.922940139708736,0.24954217788649988,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35383e4be4_2026-10-07T16-03-06.767724.json,1791388706.4849381,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,chrf,none,32.02386206481722,0.2902285722556033,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35383e4be4_2026-10-07T16-03-06.767724.json,1791388706.4849381,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,bleu,none,24.968783556587265,0.38597486522196567,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cb8124ddba_2026-10-07T16-07-19.068403.json,1791388950.9623556,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,chrf,none,43.57600514142362,0.3651406204967477,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cb8124ddba_2026-10-07T16-07-19.068403.json,1791388950.9623556,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,bleu,none,37.2209268349064,0.3628550784768577,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/31e2426e74_2026-10-07T16-17-43.381608.json,1791389565.348021,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,chrf,none,54.48605195564138,0.296050035170676,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/31e2426e74_2026-10-07T16-17-43.381608.json,1791389565.348021,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,bleu,none,25.269365682179597,0.2996719612190205,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7c7c2ef8c6_2026-10-07T15-49-08.402015.json,1791387865.1915078,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,chrf,none,44.41651296547124,0.3079028582489008,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7c7c2ef8c6_2026-10-07T15-49-08.402015.json,1791387865.1915078,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,bleu,none,23.916491615536213,0.32001635046287924,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cbc529d63e_2026-10-07T15-55-07.780077.json,1791388218.5963469,1 +v1annealC_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,chrf,none,43.077852870179214,0.2518118102903831,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cbc529d63e_2026-10-07T15-55-07.780077.json,1791388218.5963469,1 +v1annealC_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc,none,0.7986942328618063,0.009355431098990414,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfc0cb5ce4_2026-10-07T16-05-14.368438.json,1791388947.4084933,1 +v1annealC_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc_norm,none,0.8133841131664853,0.009090077190470842,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfc0cb5ce4_2026-10-07T16-05-14.368438.json,1791388947.4084933,1 +v1annealC_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc,none,0.8150163220892275,0.009059313316508697,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0790b65034_2026-10-07T16-15-52.671218.json,1791389562.1517398,1 +v1annealC_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc_norm,none,0.823721436343852,0.008890687746582126,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0790b65034_2026-10-07T16-15-52.671218.json,1791389562.1517398,1 +v1annealC_merge3_116k_120k,polymath_de_high,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4f6f7d4cdf_2026-10-07T16-15-52.635692.json,1791389567.5270302,1 +v1annealC_merge3_116k_120k,polymath_de_low,0,lm-eval,vllm,,exact_match,none,0.16,0.03292219567012406,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9351f00abb_2026-10-07T16-23-53.585943.json,1791390049.1660242,1 +v1annealC_merge3_116k_120k,polymath_de_medium,0,lm-eval,vllm,,exact_match,none,0.064,0.02197946255470202,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f8a777d141_2026-10-07T15-38-58.544542.json,1791387350.112309,1 +v1annealC_merge3_116k_120k,polymath_de_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/deb59552b5_2026-10-07T16-05-56.752121.json,1791388948.563103,1 +v1annealC_merge3_116k_120k,polymath_en_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2420516e86_2026-10-07T15-51-15.536309.json,1791388089.169667,1 +v1annealC_merge3_116k_120k,polymath_en_low,0,lm-eval,vllm,,exact_match,none,0.128,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a32da6236a_2026-10-07T15-38-57.564923.json,1791387350.6451876,1 +v1annealC_merge3_116k_120k,polymath_en_medium,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/44b1311a87_2026-10-07T16-03-31.535655.json,1791388826.961601,1 +v1annealC_merge3_116k_120k,polymath_en_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/441853b228_2026-10-07T15-49-05.384620.json,1791387960.4107387,1 +v1annealC_merge3_116k_120k,polymath_es_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1a47ad8d74_2026-10-07T15-49-16.432227.json,1791387971.1343908,1 +v1annealC_merge3_116k_120k,polymath_es_low,0,lm-eval,vllm,,exact_match,none,0.28,0.04032129030193482,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f901c698f_2026-10-07T16-21-51.732000.json,1791389924.5248687,1 +v1annealC_merge3_116k_120k,polymath_es_medium,0,lm-eval,vllm,,exact_match,none,0.056,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/82b703aae9_2026-10-07T15-51-16.445121.json,1791388089.5823123,1 +v1annealC_merge3_116k_120k,polymath_es_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e5c83a4505_2026-10-07T16-01-27.189968.json,1791388702.0557194,1 +v1annealC_merge3_116k_120k,polymath_fr_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a0814bff2a_2026-10-07T16-15-41.241152.json,1791389558.9108298,1 +v1annealC_merge3_116k_120k,polymath_fr_low,0,lm-eval,vllm,,exact_match,none,0.256,0.039191835884530846,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fa787d2540_2026-10-07T16-05-34.020442.json,1791388949.2338443,1 +v1annealC_merge3_116k_120k,polymath_fr_medium,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3fe0b794aa_2026-10-07T16-23-52.352573.json,1791390045.9472828,1 +v1annealC_merge3_116k_120k,polymath_fr_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d067aeb74e_2026-10-07T16-17-55.100318.json,1791389686.3733745,1 +v1annealC_merge3_116k_120k,polymath_it_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f4dddc821e_2026-10-07T15-47-27.581835.json,1791387859.6914704,1 +v1annealC_merge3_116k_120k,polymath_it_low,0,lm-eval,vllm,,exact_match,none,0.36,0.043105272486425976,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/533089e92d_2026-10-07T15-51-19.122222.json,1791388095.1804073,1 +v1annealC_merge3_116k_120k,polymath_it_medium,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2598f81abf_2026-10-07T16-27-58.854944.json,1791390286.5621033,1 +v1annealC_merge3_116k_120k,polymath_it_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/186a03da7d_2026-10-07T16-05-34.681472.json,1791388948.38683,1 +v1annealC_merge3_116k_120k,polymath_pt_high,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b713eff595_2026-10-07T15-53-21.498731.json,1791388218.2608812,1 +v1annealC_merge3_116k_120k,polymath_pt_low,0,lm-eval,vllm,,exact_match,none,0.248,0.03878143885933063,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c5f1e864a1_2026-10-07T16-05-36.218819.json,1791388951.1004217,1 +v1annealC_merge3_116k_120k,polymath_pt_medium,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9cf3a5b0fb_2026-10-07T16-22-02.153201.json,1791389935.5935829,1 +v1annealC_merge3_116k_120k,polymath_pt_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f6f046ec25_2026-10-07T15-47-26.737930.json,1791387863.0999937,1 +v1annealC_merge3_116k_120k,sib200_als_Latn,0,lm-eval,vllm,,acc,none,0.36764705882352944,0.0338413204567412,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/76adff773a_2026-10-07T15-50-53.935513.json,1791388091.7425127,1 +v1annealC_merge3_116k_120k,sib200_bos_Latn,0,lm-eval,vllm,,acc,none,0.44607843137254904,0.034888454513049706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/baef49894c_2026-10-07T16-07-06.419679.json,1791389065.1060648,1 +v1annealC_merge3_116k_120k,sib200_bul_Cyrl,0,lm-eval,vllm,,acc,none,0.4950980392156863,0.03509143375606784,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e35b51249a_2026-10-07T15-47-04.912108.json,1791387856.8513618,1 +v1annealC_merge3_116k_120k,sib200_cat_Latn,0,lm-eval,vllm,,acc,none,0.5294117647058824,0.03503235296367989,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc4ae48e0e_2026-10-07T15-38-50.337954.json,1791387356.5404627,1 +v1annealC_merge3_116k_120k,sib200_ces_Latn,0,lm-eval,vllm,,acc,none,0.47549019607843135,0.035050931943487976,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/643b0d03ae_2026-10-07T15-47-06.650789.json,1791387864.090461,1 +v1annealC_merge3_116k_120k,sib200_dan_Latn,0,lm-eval,vllm,,acc,none,0.4166666666666667,0.03460228327239165,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3208c2801b_2026-10-07T16-03-11.415180.json,1791388831.925503,1 +v1annealC_merge3_116k_120k,sib200_deu_Latn,0,lm-eval,vllm,,acc,none,0.45588235294117646,0.034956245220154746,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b4ec349a1_2026-10-07T16-05-03.183602.json,1791388948.1101177,1 +v1annealC_merge3_116k_120k,sib200_ell_Grek,0,lm-eval,vllm,,acc,none,0.5049019607843137,0.03509143375606784,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d230623d8b_2026-10-07T15-38-36.079932.json,1791387349.9811122,1 +v1annealC_merge3_116k_120k,sib200_eng_Latn,0,lm-eval,vllm,,acc,none,0.5049019607843137,0.03509143375606784,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d7f59816a_2026-10-07T16-03-15.505275.json,1791388829.1325715,1 +v1annealC_merge3_116k_120k,sib200_est_Latn,0,lm-eval,vllm,,acc,none,0.5637254901960784,0.03480693138457044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/70ce7d2b9a_2026-10-07T16-03-27.391086.json,1791388833.7192676,1 +v1annealC_merge3_116k_120k,sib200_eus_Latn,0,lm-eval,vllm,,acc,none,0.38235294117647056,0.034107853389047135,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6560d163ff_2026-10-07T15-38-44.788475.json,1791387352.4935834,1 +v1annealC_merge3_116k_120k,sib200_fin_Latn,0,lm-eval,vllm,,acc,none,0.5392156862745098,0.03498501649369533,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00016f496e_2026-10-07T15-47-19.824578.json,1791387861.073831,1 +v1annealC_merge3_116k_120k,sib200_fra_Latn,0,lm-eval,vllm,,acc,none,0.49019607843137253,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/863baca084_2026-10-07T16-15-32.439244.json,1791389568.5860777,1 +v1annealC_merge3_116k_120k,sib200_gle_Latn,0,lm-eval,vllm,,acc,none,0.31862745098039214,0.032702871814820796,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/91c6497f2a_2026-10-07T16-05-27.807267.json,1791388946.2073321,1 +v1annealC_merge3_116k_120k,sib200_glg_Latn,0,lm-eval,vllm,,acc,none,0.5147058823529411,0.035077938347913305,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/152a3d1e45_2026-10-07T15-38-39.144804.json,1791387357.88344,1 +v1annealC_merge3_116k_120k,sib200_hrv_Latn,0,lm-eval,vllm,,acc,none,0.4852941176470588,0.035077938347913305,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8295c8aa13_2026-10-07T15-48-47.669419.json,1791387965.1239254,1 +v1annealC_merge3_116k_120k,sib200_hun_Latn,0,lm-eval,vllm,,acc,none,0.5588235294117647,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/45780c7bcf_2026-10-07T16-23-36.819876.json,1791390052.2989383,1 +v1annealC_merge3_116k_120k,sib200_isl_Latn,0,lm-eval,vllm,,acc,none,0.5294117647058824,0.03503235296367989,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a63bb0ae0_2026-10-07T16-05-15.454078.json,1791388947.543999,1 +v1annealC_merge3_116k_120k,sib200_ita_Latn,0,lm-eval,vllm,,acc,none,0.4411764705882353,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/47fd56a5fd_2026-10-07T16-03-23.317785.json,1791388826.2143323,1 +v1annealC_merge3_116k_120k,sib200_kat_Geor,0,lm-eval,vllm,,acc,none,0.27450980392156865,0.03132179803083291,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4b87c15bbd_2026-10-07T15-38-32.989725.json,1791387348.1132448,1 +v1annealC_merge3_116k_120k,sib200_lit_Latn,0,lm-eval,vllm,,acc,none,0.4950980392156863,0.03509143375606784,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/32ec104fcb_2026-10-07T15-50-42.943444.json,1791388084.7678015,1 +v1annealC_merge3_116k_120k,sib200_lvs_Latn,0,lm-eval,vllm,,acc,none,0.35294117647058826,0.033540924375915215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3bf6fda1e7_2026-10-07T15-53-01.263290.json,1791388217.0376158,1 +v1annealC_merge3_116k_120k,sib200_mkd_Cyrl,0,lm-eval,vllm,,acc,none,0.4264705882352941,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e7c4974e67_2026-10-07T16-05-06.991841.json,1791388943.458927,1 +v1annealC_merge3_116k_120k,sib200_mlt_Latn,0,lm-eval,vllm,,acc,none,0.3480392156862745,0.03343311240488421,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99e14664f6_2026-10-07T15-38-34.494186.json,1791387351.1989322,1 +v1annealC_merge3_116k_120k,sib200_nld_Latn,0,lm-eval,vllm,,acc,none,0.5343137254901961,0.03501038327635894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2c0cd5730c_2026-10-07T15-47-00.008772.json,1791387854.2789795,1 +v1annealC_merge3_116k_120k,sib200_nob_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0eda8592ce_2026-10-07T15-47-10.745256.json,1791387866.1010985,1 +v1annealC_merge3_116k_120k,sib200_pol_Latn,0,lm-eval,vllm,,acc,none,0.5784313725490197,0.03465868196380755,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b4a6973b25_2026-10-07T15-38-48.448237.json,1791387351.5912426,1 +v1annealC_merge3_116k_120k,sib200_por_Latn,0,lm-eval,vllm,,acc,none,0.4852941176470588,0.035077938347913305,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/44e97c777a_2026-10-07T15-53-00.052840.json,1791388221.6172416,1 +v1annealC_merge3_116k_120k,sib200_ron_Latn,0,lm-eval,vllm,,acc,none,0.5980392156862745,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/eb9f40f44b_2026-10-07T15-47-04.281997.json,1791387860.8775947,1 +v1annealC_merge3_116k_120k,sib200_slk_Latn,0,lm-eval,vllm,,acc,none,0.5343137254901961,0.03501038327635894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b3a6edf67f_2026-10-07T15-52-48.213410.json,1791388210.3701973,1 +v1annealC_merge3_116k_120k,sib200_slv_Latn,0,lm-eval,vllm,,acc,none,0.49019607843137253,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5a8b2c55ba_2026-10-07T15-38-30.285823.json,1791387348.4052713,1 +v1annealC_merge3_116k_120k,sib200_spa_Latn,0,lm-eval,vllm,,acc,none,0.4852941176470588,0.035077938347913305,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3dccba00e3_2026-10-07T16-05-28.495495.json,1791388951.3201976,1 +v1annealC_merge3_116k_120k,sib200_srp_Cyrl,0,lm-eval,vllm,,acc,none,0.4411764705882353,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0330d92e94_2026-10-07T15-38-33.569088.json,1791387351.5901031,1 +v1annealC_merge3_116k_120k,sib200_swe_Latn,0,lm-eval,vllm,,acc,none,0.5441176470588235,0.034956245220154746,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4e395fdabc_2026-10-07T15-50-44.730169.json,1791388087.1952124,1 +v1annealC_merge3_116k_120k,sib200_tur_Latn,0,lm-eval,vllm,,acc,none,0.47549019607843135,0.035050931943487976,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d42349c19b_2026-10-07T15-46-56.337617.json,1791387861.070203,1 +v1annealC_merge3_116k_120k,sib200_ukr_Cyrl,0,lm-eval,vllm,,acc,none,0.49019607843137253,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a6410f6508_2026-10-07T15-53-14.585462.json,1791388219.0286233,1 +v1annealC_merge3_116k_120k,social_iqa,0,lm-eval,vllm,,acc,none,0.5056294779938587,0.01131335342337948,1954,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6700f42593_2026-10-07T16-15-41.418134.json,1791389568.4191737,1 +v1annealC_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_exact,none,74.83130904183535,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fb265e80_2026-10-07T16-33-50.737166.json,1791388939.8781233,1 +v1annealC_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_f1,none,81.88184947382115,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fb265e80_2026-10-07T16-33-50.737166.json,1791388939.8781233,1 +v1annealC_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_exact,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fb265e80_2026-10-07T16-33-50.737166.json,1791388939.8781233,1 +v1annealC_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_f1,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fb265e80_2026-10-07T16-33-50.737166.json,1791388939.8781233,1 +v1annealC_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_exact,none,58.0982060136444,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fb265e80_2026-10-07T16-33-50.737166.json,1791388939.8781233,1 +v1annealC_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_f1,none,59.81720851812117,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fb265e80_2026-10-07T16-33-50.737166.json,1791388939.8781233,1 +v1annealC_merge3_116k_120k,squadv2,10,lm-eval,vllm,,exact,none,37.36208203486903,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fb265e80_2026-10-07T16-33-50.737166.json,1791388939.8781233,1 +v1annealC_merge3_116k_120k,squadv2,10,lm-eval,vllm,,f1,none,40.88230469812278,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a4fb265e80_2026-10-07T16-33-50.737166.json,1791388939.8781233,1 +v1annealC_merge3_116k_120k,winogrande,0,lm-eval,vllm,,acc,none,0.7277032359905288,0.0125106979914538,1267,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/972e4ee4d7_2026-10-07T15-51-15.822371.json,1791388094.3851404,1 +v1annealC_merge3_116k_120k,wsc273,0,lm-eval,vllm,,acc,none,0.7985347985347986,0.024319939627182593,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/db899577e3_2026-10-07T16-21-28.670529.json,1791389923.1853464,1 +v1annealC_merge3_116k_120k,xcopa:et,0,lighteval,hf/accelerate,,acc,none,0.618,0.02175082059125084,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e6933ee2ff/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-05-41.113146.json,1791389141.2012763,1 +v1annealC_merge3_116k_120k,xcopa:it,0,lighteval,hf/accelerate,,acc,none,0.684,0.02081235951585585,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/488e0e69a9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-26-07.019050.json,1791390367.1286287,1 +v1annealC_merge3_116k_120k,xcopa:tr,0,lighteval,hf/accelerate,,acc,none,0.658,0.021236147199899268,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3d7a3036f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealC_merge3_116k_120k/results_2026-10-07T16-05-42.593409.json,1791389143.0182416,1 +v1annealC_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc,none,0.489,0.01581547119529257,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93b9fa303d_2026-10-07T16-03-31.050553.json,1791388833.9849243,1 +v1annealC_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc_norm,none,0.445,0.015723301886761007,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93b9fa303d_2026-10-07T16-03-31.050553.json,1791388833.9849243,1 +v1annealC_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc,none,0.655,0.015039986742055365,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3a1f9997b2_2026-10-07T16-27-48.684603.json,1791390295.3304944,1 +v1annealC_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc_norm,none,0.61,0.01543172505386673,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3a1f9997b2_2026-10-07T16-27-48.684603.json,1791390295.3304944,1 +v1annealC_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc,none,0.468,0.015786868759359002,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f96bab6f65_2026-10-07T15-47-23.817200.json,1791387865.4692025,1 +v1annealC_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc_norm,none,0.405,0.01553113699045296,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f96bab6f65_2026-10-07T15-47-23.817200.json,1791387865.4692025,1 +v1annealC_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc,none,0.481,0.015807874268505835,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3c99b9796_2026-10-07T15-38-43.333579.json,1791387354.6272528,1 +v1annealC_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc_norm,none,0.413,0.015577986829936455,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3c99b9796_2026-10-07T15-38-43.333579.json,1791387354.6272528,1 +v1annealC_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc,none,0.459,0.015766025737882314,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e1736a2eea_2026-10-07T16-27-37.001052.json,1791390288.7524745,1 +v1annealC_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc_norm,none,0.431,0.01566794448817344,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e1736a2eea_2026-10-07T16-27-37.001052.json,1791390288.7524745,1 +v1annealC_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc,none,0.395,0.015466551464829328,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4988c73d7e_2026-10-07T15-51-02.810796.json,1791388093.3972406,1 +v1annealC_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc_norm,none,0.373,0.015300493622922927,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4988c73d7e_2026-10-07T15-51-02.810796.json,1791388093.3972406,1 +v1annealC_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.46,0.015768596914394403,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a18b880313_2026-10-07T16-05-09.863996.json,1791388941.737439,1 +v1annealC_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.433,0.01567663091218125,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a18b880313_2026-10-07T16-05-09.863996.json,1791388941.737439,1 +v1annealC_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.432,0.015672320237336324,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b71cb22ba5_2026-10-07T15-38-35.203947.json,1791387347.74303,1 +v1annealC_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.373,0.015300493622922927,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b71cb22ba5_2026-10-07T15-38-35.203947.json,1791387347.74303,1 +v1annealC_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@1,all,0.020833333333333332,0.01580949506150076,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ff58329021_2026-10-08T23-19-11.700561.json,1791500362.4447186,1 +v1annealC_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@16,all,0.09623655819703807,0.04805524091660937,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ff58329021_2026-10-08T23-19-11.700561.json,1791500362.4447186,1 +v1annealC_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@32,all,0.13333333333333333,0.06312427686319991,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ff58329021_2026-10-08T23-19-11.700561.json,1791500362.4447186,1 +v1annealC_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@4,all,0.05077771598071932,0.03289099057875849,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ff58329021_2026-10-08T23-19-11.700561.json,1791500362.4447186,1 +v1annealC_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,think_closed,all,0.021875,0.012638421794661313,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ff58329021_2026-10-08T23-19-11.700561.json,1791500362.4447186,1 +v1annealC_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@1,all,0.035416666666666666,0.0181497139607829,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/eb0479f520_2026-10-08T23-18-54.760693.json,1791500348.3207586,1 +v1annealC_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@16,all,0.1552238849449073,0.06480967151013789,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/eb0479f520_2026-10-08T23-18-54.760693.json,1791500348.3207586,1 +v1annealC_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@32,all,0.16666666666666666,0.06920456654478331,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/eb0479f520_2026-10-08T23-18-54.760693.json,1791500348.3207586,1 +v1annealC_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@4,all,0.09368743047830923,0.04336070908249595,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/eb0479f520_2026-10-08T23-18-54.760693.json,1791500348.3207586,1 +v1annealC_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,think_closed,all,0.041666666666666664,0.016229909478670045,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/eb0479f520_2026-10-08T23-18-54.760693.json,1791500348.3207586,1 +v1annealC_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@1,all,0.1875,0.034956474767990096,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8459f48ee9_2026-10-08T23-22-36.265301.json,1791500350.994723,1 +v1annealC_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@16,all,0.6346132174599807,0.06987494296652794,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8459f48ee9_2026-10-08T23-22-36.265301.json,1791500350.994723,1 +v1annealC_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@32,all,0.7,0.07337993857053428,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8459f48ee9_2026-10-08T23-22-36.265301.json,1791500350.994723,1 +v1annealC_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@4,all,0.419021829810901,0.058829320297457965,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8459f48ee9_2026-10-08T23-22-36.265301.json,1791500350.994723,1 +v1annealC_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,think_closed,all,0.20390625,0.04010995473133421,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8459f48ee9_2026-10-08T23-22-36.265301.json,1791500350.994723,1 +v1annealC_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,pass@1,all,0.3005050505050505,0.027440112756842435,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/9df3dfd753_2026-10-08T23-25-36.203459.json,1791500349.948173,1 +v1annealC_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,think_closed,all,0.2222222222222222,0.024919612448994186,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/9df3dfd753_2026-10-08T23-25-36.203459.json,1791500349.948173,1 +v1annealC_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@1,all,0.42378048780487804,0.03271346348634639,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/5e2b478ffd_2026-10-08T23-04-01.603951.json,1791500346.3725474,1 +v1annealC_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@16,all,0.6554505621119997,0.036245672523329435,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/5e2b478ffd_2026-10-08T23-04-01.603951.json,1791500346.3725474,1 +v1annealC_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@1,all,0.11310679611650486,0.011218966426756407,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c697bcd6f0_2026-10-08T23-31-01.368365.json,1791500352.0215113,1 +v1annealC_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@4,all,0.1766990291262136,0.0168234412516812,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c697bcd6f0_2026-10-08T23-31-01.368365.json,1791500352.0215113,1 +v1annealC_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,think_closed,all,0.23058252427184467,0.01543396222349285,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c697bcd6f0_2026-10-08T23-31-01.368365.json,1791500352.0215113,1 +v1annealC_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@1,all,0.12279843444227005,0.012200818644292354,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/22b03462c7_2026-10-08T23-07-43.032498.json,1791500359.2231526,1 +v1annealC_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@4,all,0.18691641039977636,0.016610287698234232,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/22b03462c7_2026-10-08T23-07-43.032498.json,1791500359.2231526,1 +v1annealC_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@1,all,0.3465,0.016633666394256886,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d335e49ab6_2026-10-08T23-30-30.019166.json,1791500349.9558094,1 +v1annealC_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@4,all,0.56,0.022221331534143057,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d335e49ab6_2026-10-08T23-30-30.019166.json,1791500349.9558094,1 +v1annealC_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,think_closed,all,0.452,0.017748860360264723,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d335e49ab6_2026-10-08T23-30-30.019166.json,1791500349.9558094,1 +v1annealC_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@1,all,0.529125,0.01976875884831432,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/dcf477d48d_2026-10-08T23-06-08.565707.json,1791500357.3898866,1 +v1annealC_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@16,all,0.6721941732352972,0.020741175111191817,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/dcf477d48d_2026-10-08T23-06-08.565707.json,1791500357.3898866,1 +v1annealC_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.006309235422212681,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/0125705e7f_2026-10-08T23-11-14.741418.json,1791500353.2934072,1 +v1annealC_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/0125705e7f_2026-10-08T23-11-14.741418.json,1791500353.2934072,1 +v1annealC_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,think_closed,all,0.032,0.013312618316905691,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/0125705e7f_2026-10-08T23-11-14.741418.json,1791500353.2934072,1 +v1annealC_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@1,all,0.126,0.018970265357710087,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b9cc06913a_2026-10-08T23-09-29.541805.json,1791500362.2317693,1 +v1annealC_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@4,all,0.336,0.04241728193144408,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b9cc06913a_2026-10-08T23-09-29.541805.json,1791500362.2317693,1 +v1annealC_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,think_closed,all,0.816,0.026812370760647995,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b9cc06913a_2026-10-08T23-09-29.541805.json,1791500362.2317693,1 +v1annealC_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@1,all,0.054,0.01809116697674987,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f75b47b29b_2026-10-08T23-11-26.292253.json,1791500359.2354283,1 +v1annealC_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@4,all,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f75b47b29b_2026-10-08T23-11-26.292253.json,1791500359.2354283,1 +v1annealC_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,think_closed,all,0.148,0.028694160359029105,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f75b47b29b_2026-10-08T23-11-26.292253.json,1791500359.2354283,1 +v1annealC_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c88c3064a1_2026-10-08T23-11-29.473978.json,1791500362.5136576,1 +v1annealC_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c88c3064a1_2026-10-08T23-11-29.473978.json,1791500362.5136576,1 +v1annealC_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,think_closed,all,0.014,0.007130126904720514,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c88c3064a1_2026-10-08T23-11-29.473978.json,1791500362.5136576,1 +v1annealC_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@1,all,0.012,0.006872103495409022,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b15d01ebd3_2026-10-08T23-11-26.361252.json,1791500352.7780645,1 +v1annealC_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@4,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b15d01ebd3_2026-10-08T23-11-26.361252.json,1791500352.7780645,1 +v1annealC_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,think_closed,all,0.08,0.017413380098407455,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b15d01ebd3_2026-10-08T23-11-26.361252.json,1791500352.7780645,1 +v1annealC_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@1,all,0.16,0.03292219567012406,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/fc5a1a583a_2026-10-08T23-08-08.429556.json,1791500363.9302192,1 +v1annealC_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@4,all,0.16,0.03292219567012406,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/fc5a1a583a_2026-10-08T23-08-08.429556.json,1791500363.9302192,1 +v1annealC_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,think_closed,all,0.872,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/fc5a1a583a_2026-10-08T23-08-08.429556.json,1791500363.9302192,1 +v1annealC_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@1,all,0.048,0.013227537258896074,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a16739e693_2026-10-08T23-11-09.858965.json,1791500348.4929137,1 +v1annealC_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@4,all,0.112,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a16739e693_2026-10-08T23-11-09.858965.json,1791500348.4929137,1 +v1annealC_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,think_closed,all,0.136,0.024180770819379492,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a16739e693_2026-10-08T23-11-09.858965.json,1791500348.4929137,1 +v1annealC_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.006309235422212681,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8f104385df_2026-10-08T23-11-14.544528.json,1791500350.0992823,1 +v1annealC_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8f104385df_2026-10-08T23-11-14.544528.json,1791500350.0992823,1 +v1annealC_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,think_closed,all,0.096,0.023032935744977407,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8f104385df_2026-10-08T23-11-14.544528.json,1791500350.0992823,1 +v1annealC_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@1,all,0.006,0.003436051747704511,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ce50504bec_2026-10-08T23-11-20.195824.json,1791500354.7041993,1 +v1annealC_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@4,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ce50504bec_2026-10-08T23-11-20.195824.json,1791500354.7041993,1 +v1annealC_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,think_closed,all,0.02,0.009245748805139686,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ce50504bec_2026-10-08T23-11-20.195824.json,1791500354.7041993,1 +v1annealC_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@1,all,0.176,0.02289949992410737,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a057f5663c_2026-10-08T23-09-29.633805.json,1791500357.5889351,1 +v1annealC_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@4,all,0.416,0.044263142753894154,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a057f5663c_2026-10-08T23-09-29.633805.json,1791500357.5889351,1 +v1annealC_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,think_closed,all,0.856,0.025282915307606693,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a057f5663c_2026-10-08T23-09-29.633805.json,1791500357.5889351,1 +v1annealC_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@1,all,0.03,0.01121634751658949,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ce1de1a6e9_2026-10-08T23-11-09.357594.json,1791500341.5424542,1 +v1annealC_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@4,all,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ce1de1a6e9_2026-10-08T23-11-09.357594.json,1791500341.5424542,1 +v1annealC_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,think_closed,all,0.146,0.02912487020599627,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ce1de1a6e9_2026-10-08T23-11-09.357594.json,1791500341.5424542,1 +v1annealC_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@1,all,0.006,0.006,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d5196d051e_2026-10-08T23-11-26.349572.json,1791500360.6049967,1 +v1annealC_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d5196d051e_2026-10-08T23-11-26.349572.json,1791500360.6049967,1 +v1annealC_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,think_closed,all,0.038,0.014495828098389705,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d5196d051e_2026-10-08T23-11-26.349572.json,1791500360.6049967,1 +v1annealC_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c72adad78f_2026-10-08T23-11-13.406920.json,1791500349.9509513,1 +v1annealC_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c72adad78f_2026-10-08T23-11-13.406920.json,1791500349.9509513,1 +v1annealC_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,think_closed,all,0.024,0.011152896340152792,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c72adad78f_2026-10-08T23-11-13.406920.json,1791500349.9509513,1 +v1annealC_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@1,all,0.178,0.022327474757174354,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8344c28fc0_2026-10-08T23-09-16.018897.json,1791500349.8340137,1 +v1annealC_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@4,all,0.4,0.043994134506405984,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8344c28fc0_2026-10-08T23-09-16.018897.json,1791500349.8340137,1 +v1annealC_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,think_closed,all,0.83,0.02549509756796392,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8344c28fc0_2026-10-08T23-09-16.018897.json,1791500349.8340137,1 +v1annealC_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@1,all,0.03,0.008798826901281196,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/4e86a921e1_2026-10-08T23-11-33.041515.json,1791500363.6865194,1 +v1annealC_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@4,all,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/4e86a921e1_2026-10-08T23-11-33.041515.json,1791500363.6865194,1 +v1annealC_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,think_closed,all,0.108,0.021124821052878273,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/4e86a921e1_2026-10-08T23-11-33.041515.json,1791500363.6865194,1 +v1annealC_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2c90d7ce60_2026-10-08T23-11-23.738870.json,1791500363.7827075,1 +v1annealC_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2c90d7ce60_2026-10-08T23-11-23.738870.json,1791500363.7827075,1 +v1annealC_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,think_closed,all,0.032,0.012370620763103043,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2c90d7ce60_2026-10-08T23-11-23.738870.json,1791500363.7827075,1 +v1annealC_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@1,all,0.01,0.005956833971812705,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/229b215d54_2026-10-08T23-11-18.623932.json,1791500361.377052,1 +v1annealC_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@4,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/229b215d54_2026-10-08T23-11-18.623932.json,1791500361.377052,1 +v1annealC_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,think_closed,all,0.05,0.01237844119635477,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/229b215d54_2026-10-08T23-11-18.623932.json,1791500361.377052,1 +v1annealC_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@1,all,0.144,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ac03b7ca2b_2026-10-08T23-09-18.622652.json,1791500356.3679934,1 +v1annealC_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@4,all,0.144,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ac03b7ca2b_2026-10-08T23-09-18.622652.json,1791500356.3679934,1 +v1annealC_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,think_closed,all,0.848,0.032241027759172654,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ac03b7ca2b_2026-10-08T23-09-18.622652.json,1791500356.3679934,1 +v1annealC_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@1,all,0.05,0.013912166872805047,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/436b1ec276_2026-10-08T23-11-20.665777.json,1791500353.3565927,1 +v1annealC_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@4,all,0.12,0.029182407426835203,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/436b1ec276_2026-10-08T23-11-20.665777.json,1791500353.3565927,1 +v1annealC_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,think_closed,all,0.132,0.024523852773141286,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/436b1ec276_2026-10-08T23-11-20.665777.json,1791500353.3565927,1 +v1annealC_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7b4bbb15a4_2026-10-08T23-11-17.183811.json,1791500348.3184838,1 +v1annealC_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7b4bbb15a4_2026-10-08T23-11-17.183811.json,1791500348.3184838,1 +v1annealC_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,think_closed,all,0.024,0.009598386961258882,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7b4bbb15a4_2026-10-08T23-11-17.183811.json,1791500348.3184838,1 +v1annealC_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/3b6651ace6_2026-10-08T23-11-17.585142.json,1791500351.3559654,1 +v1annealC_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/3b6651ace6_2026-10-08T23-11-17.585142.json,1791500351.3559654,1 +v1annealC_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,think_closed,all,0.036,0.014397580441888321,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/3b6651ace6_2026-10-08T23-11-17.585142.json,1791500351.3559654,1 +v1annealC_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@1,all,0.156,0.025026437633933467,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/4d354f39d7_2026-10-08T23-08-09.373110.json,1791500349.9478426,1 +v1annealC_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@4,all,0.304,0.041307657651398745,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/4d354f39d7_2026-10-08T23-08-09.373110.json,1791500349.9478426,1 +v1annealC_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,think_closed,all,0.854,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/4d354f39d7_2026-10-08T23-08-09.373110.json,1791500349.9478426,1 +v1annealC_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@1,all,0.03,0.010472698761772856,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7c54dca6b0_2026-10-08T23-11-07.699486.json,1791500344.6787825,1 +v1annealC_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@4,all,0.08,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7c54dca6b0_2026-10-08T23-11-07.699486.json,1791500344.6787825,1 +v1annealC_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,think_closed,all,0.134,0.025167823800215816,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7c54dca6b0_2026-10-08T23-11-07.699486.json,1791500344.6787825,1 +v1annealC_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f7c280d544_2026-10-08T23-11-30.799202.json,1791500361.3867989,1 +v1annealC_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f7c280d544_2026-10-08T23-11-30.799202.json,1791500361.3867989,1 +v1annealC_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,think_closed,all,0.048,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealC_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f7c280d544_2026-10-08T23-11-30.799202.json,1791500361.3867989,1 diff --git a/results/v1annealTT_merge3_116k_120k.flag-evals-471.tasks.csv b/results/v1annealTT_merge3_116k_120k.flag-evals-471.tasks.csv new file mode 100644 index 0000000..4be1ef0 --- /dev/null +++ b/results/v1annealTT_merge3_116k_120k.flag-evals-471.tasks.csv @@ -0,0 +1,2124 @@ +checkpoint,task,n_shot,harness,backend,is_group,metric,filter,value,stderr,n_samples,results_file,result_time,n_files +v1annealTT_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,accuracy_avg,,0.03,0.0031622776601683785,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5aacf76063/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-11-35.928823.json,1791389491.7797077,1 +v1annealTT_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,solved_avg,,0.9,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5aacf76063/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-11-35.928823.json,1791389491.7797077,1 +v1annealTT_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,accuracy_avg,,0.0,0.0,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/11d2f20f3a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-45-46.568883.json,1791391542.3962529,1 +v1annealTT_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,solved_avg,,0.0,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/11d2f20f3a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-45-46.568883.json,1791391542.3962529,1 +v1annealTT_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,accuracy_avg,,0.07499999999999998,4.388541835720876e-18,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a6c3bd9a44/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-38.614318.json,1791389074.249048,1 +v1annealTT_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,solved_avg,,3.0,,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a6c3bd9a44/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-38.614318.json,1791389074.249048,1 +v1annealTT_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,accuracy_avg,,0.3148148148148148,0.020248730137675326,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5ad3edef98/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-38.253552.json,1791390332.3301911,1 +v1annealTT_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,solved_avg,,62.333333333333336,,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5ad3edef98/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-38.253552.json,1791390332.3301911,1 +v1annealTT_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,python_pass@1,,0.1402439024390244,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f798ce1030/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T15-41-19.740121.json,1791387676.0953984,1 +v1annealTT_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,sh_pass@1,,0.06962025316455696,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f798ce1030/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T15-41-19.740121.json,1791387676.0953984,1 +v1annealTT_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,accuracy_avg,,0.3296116504854369,0.0026979501618985572,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/43e51d338e/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-33-09.360460.json,1791390785.1975114,1 +v1annealTT_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,solved_avg,,169.75,,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/43e51d338e/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-33-09.360460.json,1791390785.1975114,1 +v1annealTT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_avg,,0.12850619699934765,0.000967540572354294,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/612af47510/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-35-32.708821.json,1791390929.1712918,1 +v1annealTT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_easy_avg,,0.2811355311355311,0.0026223115500506136,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/612af47510/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-35-32.708821.json,1791390929.1712918,1 +v1annealTT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_hard_avg,,0.0,0.0,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/612af47510/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-35-32.708821.json,1791390929.1712918,1 +v1annealTT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_medium_avg,,0.07038834951456309,0.0024271844660194164,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/612af47510/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-35-32.708821.json,1791390929.1712918,1 +v1annealTT_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,solved_avg,,65.66666666666667,,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/612af47510/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T16-35-32.708821.json,1791390929.1712918,1 +v1annealTT_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,accuracy,,0.22,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0b6f782778/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T15-55-11.426676.json,1791388503.1391752,1 +v1annealTT_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,num_solved,,110,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0b6f782778/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1annealTT_merge3_116k_120k/results_2026-10-07T15-55-11.426676.json,1791388503.1391752,1 +v1annealTT_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc,none,0.2826086956521739,0.02975452853823324,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8046ca0f1c_2026-10-07T15-36-42.179011.json,1791387224.3325171,1 +v1annealTT_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc_norm,none,0.24782608695652175,0.028530862595410027,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8046ca0f1c_2026-10-07T15-36-42.179011.json,1791387224.3325171,1 +v1annealTT_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc,none,0.6151877133105802,0.014218371065251156,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a64b507020_2026-10-07T15-47-28.960663.json,1791387861.6640174,1 +v1annealTT_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc_norm,none,0.6382252559726962,0.014041957945037995,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a64b507020_2026-10-07T15-47-28.960663.json,1791387861.6640174,1 +v1annealTT_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc,none,0.6203071672354948,0.01418211986697471,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f14ebda99_2026-10-07T15-37-34.983820.json,1791387226.22804,1 +v1annealTT_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc_norm,none,0.6527303754266212,0.013913034529620455,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f14ebda99_2026-10-07T15-37-34.983820.json,1791387226.22804,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc,none,0.5426621160409556,0.014558106543923992,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac12fe94fe_2026-10-07T15-50-17.976573.json,1791387975.2434611,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc_norm,none,0.575938566552901,0.014441889627464344,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac12fe94fe_2026-10-07T15-50-17.976573.json,1791387975.2434611,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc,none,0.5426621160409556,0.014558106543923992,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f38fdbe7b_2026-10-07T15-45-57.147352.json,1791387730.9596925,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc_norm,none,0.5691126279863481,0.014471133392642476,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f38fdbe7b_2026-10-07T15-45-57.147352.json,1791387730.9596925,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc,none,0.5511945392491467,0.014534599585097566,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e065ee3b43_2026-10-07T15-45-57.466063.json,1791387724.1836505,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc_norm,none,0.5810580204778157,0.01441810695363902,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e065ee3b43_2026-10-07T15-45-57.466063.json,1791387724.1836505,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc,none,0.5034129692832765,0.014611050403244159,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b40f8d4783_2026-10-07T16-12-34.356622.json,1791389323.0072474,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc_norm,none,0.5452218430034129,0.014551507060836232,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b40f8d4783_2026-10-07T16-12-34.356622.json,1791389323.0072474,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc,none,0.5409556313993175,0.01456229107360112,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c928cdfd0c_2026-10-07T15-52-18.564316.json,1791388090.4405158,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc_norm,none,0.5742320819112628,0.014449464278868677,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c928cdfd0c_2026-10-07T15-52-18.564316.json,1791388090.4405158,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc,none,0.5631399317406144,0.014494421584256512,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0ecd326d42_2026-10-07T15-52-10.315293.json,1791388094.1610754,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc_norm,none,0.6023890784982935,0.014301752223279514,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0ecd326d42_2026-10-07T15-52-10.315293.json,1791388094.1610754,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc,none,0.5102389078498294,0.014608326906285005,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a255192298_2026-10-07T15-37-39.312378.json,1791387230.1573207,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc_norm,none,0.5477815699658704,0.014544519880633823,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a255192298_2026-10-07T15-37-39.312378.json,1791387230.1573207,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc,none,0.49402730375426623,0.014610348300255798,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/077b75db86_2026-10-07T16-18-19.339708.json,1791389672.507249,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc_norm,none,0.5324232081911263,0.014580637569995414,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/077b75db86_2026-10-07T16-18-19.339708.json,1791389672.507249,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc,none,0.5588737201365188,0.014509747749064824,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fcb69b7121_2026-10-07T15-50-08.697051.json,1791387971.4445524,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc_norm,none,0.5947098976109215,0.01434686906022932,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fcb69b7121_2026-10-07T15-50-08.697051.json,1791387971.4445524,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc,none,0.48890784982935154,0.014607794914013027,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/73e6ed0f99_2026-10-07T16-18-47.687342.json,1791389691.3960083,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc_norm,none,0.5392491467576792,0.014566303676636534,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/73e6ed0f99_2026-10-07T16-18-47.687342.json,1791389691.3960083,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc,none,0.5025597269624573,0.014611199329843819,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/21034f31e3_2026-10-07T15-39-40.668428.json,1791387350.5841863,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc_norm,none,0.5460750853242321,0.014549221105171829,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/21034f31e3_2026-10-07T15-39-40.668428.json,1791387350.5841863,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc,none,0.5622866894197952,0.01449757388110822,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09d1c8acb1_2026-10-07T15-39-45.011215.json,1791387345.0069704,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc_norm,none,0.6032423208191127,0.014296513020180628,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09d1c8acb1_2026-10-07T15-39-45.011215.json,1791387345.0069704,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc,none,0.523037542662116,0.014595873205358168,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/128c3f4449_2026-10-07T15-51-59.215475.json,1791388088.4294045,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc_norm,none,0.5486348122866894,0.014542104569955378,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/128c3f4449_2026-10-07T15-51-59.215475.json,1791388088.4294045,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc,none,0.5162116040955631,0.014603708567414945,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb095e3b39_2026-10-07T16-13-10.261746.json,1791389325.4852183,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc_norm,none,0.53839590443686,0.014568245550296302,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb095e3b39_2026-10-07T16-13-10.261746.json,1791389325.4852183,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc,none,0.5349829351535836,0.014575583922019714,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0f5705a9f9_2026-10-07T15-37-39.857426.json,1791387227.8600388,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc_norm,none,0.5827645051194539,0.014409825518403108,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0f5705a9f9_2026-10-07T15-37-39.857426.json,1791387227.8600388,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc,none,0.5477815699658704,0.014544519880633823,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8ba65a61c_2026-10-07T15-48-11.886288.json,1791387854.3616648,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc_norm,none,0.5631399317406144,0.014494421584256512,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8ba65a61c_2026-10-07T15-48-11.886288.json,1791387854.3616648,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc,none,0.5273037542662116,0.014589589101986081,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6ba6fd692_2026-10-07T15-54-07.845205.json,1791388217.4200156,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc_norm,none,0.5537542662116041,0.014526705548539945,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6ba6fd692_2026-10-07T15-54-07.845205.json,1791388217.4200156,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc,none,0.5639931740614335,0.014491225699230854,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/164bf90285_2026-10-07T16-20-41.180298.json,1791389808.310024,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc_norm,none,0.6023890784982935,0.014301752223279514,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/164bf90285_2026-10-07T16-20-41.180298.json,1791389808.310024,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc,none,0.5452218430034129,0.014551507060836232,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c23fbd149a_2026-10-07T16-22-52.158018.json,1791389935.5240886,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc_norm,none,0.591296928327645,0.014365750345427017,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c23fbd149a_2026-10-07T16-22-52.158018.json,1791389935.5240886,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc,none,0.5477815699658704,0.014544519880633823,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/82f5340576_2026-10-07T15-49-58.400065.json,1791387964.0061963,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc_norm,none,0.575938566552901,0.014441889627464344,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/82f5340576_2026-10-07T15-49-58.400065.json,1791387964.0061963,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc,none,0.5332764505119454,0.0145789958596058,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6c0206b2b8_2026-10-07T15-54-11.978912.json,1791388218.89723,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc_norm,none,0.5691126279863481,0.014471133392642476,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6c0206b2b8_2026-10-07T15-54-11.978912.json,1791388218.89723,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc,none,0.5366894197952219,0.014572000527756918,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/020f2f9d44_2026-10-07T16-20-35.872158.json,1791389803.2294586,1 +v1annealTT_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc_norm,none,0.5716723549488054,0.014460496367599081,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/020f2f9d44_2026-10-07T16-20-35.872158.json,1791389803.2294586,1 +v1annealTT_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc,none,0.8615319865319865,0.007087264269592783,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e28e18e548_2026-10-07T15-53-37.841464.json,1791388207.3091629,1 +v1annealTT_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc_norm,none,0.8703703703703703,0.006892430287197678,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e28e18e548_2026-10-07T15-53-37.841464.json,1791388207.3091629,1 +v1annealTT_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/65a9c8ba7b_2026-10-07T15-45-09.005599.json,1791387725.9398274,1 +v1annealTT_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc_norm,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/65a9c8ba7b_2026-10-07T15-45-09.005599.json,1791387725.9398274,1 +v1annealTT_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4808bfcdb7_2026-10-07T15-51-03.811578.json,1791388083.9576044,1 +v1annealTT_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc_norm,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4808bfcdb7_2026-10-07T15-51-03.811578.json,1791388083.9576044,1 +v1annealTT_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/249d32ba69_2026-10-07T15-51-02.688312.json,1791388086.3328242,1 +v1annealTT_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc_norm,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/249d32ba69_2026-10-07T15-51-02.688312.json,1791388086.3328242,1 +v1annealTT_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93d09c7995_2026-10-07T16-11-43.785995.json,1791389318.3808548,1 +v1annealTT_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc_norm,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93d09c7995_2026-10-07T16-11-43.785995.json,1791389318.3808548,1 +v1annealTT_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc,none,0.9122222222222223,0.009437626131205126,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/87b889dd10_2026-10-07T15-44-50.295454.json,1791387718.1723197,1 +v1annealTT_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc_norm,none,0.9122222222222223,0.009437626131205126,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/87b889dd10_2026-10-07T15-44-50.295454.json,1791387718.1723197,1 +v1annealTT_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99762fa788_2026-10-07T15-51-12.813194.json,1791388094.098559,1 +v1annealTT_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc_norm,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99762fa788_2026-10-07T15-51-12.813194.json,1791388094.098559,1 +v1annealTT_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc,none,0.8666666666666667,0.011337454811236778,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/84df350878_2026-10-07T15-49-10.922357.json,1791387970.7225003,1 +v1annealTT_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc_norm,none,0.8666666666666667,0.011337454811236778,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/84df350878_2026-10-07T15-49-10.922357.json,1791387970.7225003,1 +v1annealTT_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc,none,0.8855555555555555,0.010617576963634174,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f9dd2aedcd_2026-10-07T16-11-30.818943.json,1791389314.4588442,1 +v1annealTT_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc_norm,none,0.8855555555555555,0.010617576963634174,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f9dd2aedcd_2026-10-07T16-11-30.818943.json,1791389314.4588442,1 +v1annealTT_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc,none,0.9133333333333333,0.009383413499032888,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f870d53f2_2026-10-07T15-44-57.596200.json,1791387724.6551287,1 +v1annealTT_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc_norm,none,0.9133333333333333,0.009383413499032888,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f870d53f2_2026-10-07T15-44-57.596200.json,1791387724.6551287,1 +v1annealTT_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9b14009aec_2026-10-07T15-43-16.342163.json,1791387601.653521,1 +v1annealTT_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc_norm,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9b14009aec_2026-10-07T15-43-16.342163.json,1791387601.653521,1 +v1annealTT_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.010481480680812848,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/13e4959e77_2026-10-07T15-49-12.235022.json,1791387973.1406465,1 +v1annealTT_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc_norm,none,0.8888888888888888,0.010481480680812848,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/13e4959e77_2026-10-07T15-49-12.235022.json,1791387973.1406465,1 +v1annealTT_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c4012eb146_2026-10-07T15-57-33.786959.json,1791388466.7642283,1 +v1annealTT_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc_norm,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c4012eb146_2026-10-07T15-57-33.786959.json,1791388466.7642283,1 +v1annealTT_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc,none,0.8777777777777778,0.010924146933565216,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0b9fb65f35_2026-10-07T15-42-47.041113.json,1791387588.313306,1 +v1annealTT_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc_norm,none,0.8777777777777778,0.010924146933565216,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0b9fb65f35_2026-10-07T15-42-47.041113.json,1791387588.313306,1 +v1annealTT_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc,none,0.89,0.010435457652553744,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e207c5451a_2026-10-07T15-36-44.655518.json,1791387231.108012,1 +v1annealTT_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc_norm,none,0.89,0.010435457652553744,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e207c5451a_2026-10-07T15-36-44.655518.json,1791387231.108012,1 +v1annealTT_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc,none,0.8677777777777778,0.011297351524647564,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/794869683d_2026-10-07T15-47-06.930745.json,1791387852.4870136,1 +v1annealTT_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc_norm,none,0.8677777777777778,0.011297351524647564,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/794869683d_2026-10-07T15-47-06.930745.json,1791387852.4870136,1 +v1annealTT_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a894d2fcee_2026-10-07T16-11-41.427845.json,1791389325.981709,1 +v1annealTT_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc_norm,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a894d2fcee_2026-10-07T16-11-41.427845.json,1791389325.981709,1 +v1annealTT_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc,none,0.8944444444444445,0.010247959196000194,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bab46afe47_2026-10-07T15-42-54.334369.json,1791387590.721384,1 +v1annealTT_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc_norm,none,0.8944444444444445,0.010247959196000194,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bab46afe47_2026-10-07T15-42-54.334369.json,1791387590.721384,1 +v1annealTT_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc,none,0.8733333333333333,0.011092804100207776,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b3ff9091b5_2026-10-07T15-42-58.938603.json,1791387600.5745196,1 +v1annealTT_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc_norm,none,0.8733333333333333,0.011092804100207776,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b3ff9091b5_2026-10-07T15-42-58.938603.json,1791387600.5745196,1 +v1annealTT_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/374eadce58_2026-10-07T15-36-48.139909.json,1791387234.2130213,1 +v1annealTT_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc_norm,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/374eadce58_2026-10-07T15-36-48.139909.json,1791387234.2130213,1 +v1annealTT_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f8657908d_2026-10-07T15-43-01.188442.json,1791387594.3683414,1 +v1annealTT_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc_norm,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f8657908d_2026-10-07T15-43-01.188442.json,1791387594.3683414,1 +v1annealTT_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc,none,0.8933333333333333,0.010295354033282278,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc03c15acc_2026-10-07T15-42-47.779992.json,1791387593.001437,1 +v1annealTT_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc_norm,none,0.8933333333333333,0.010295354033282278,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc03c15acc_2026-10-07T15-42-47.779992.json,1791387593.001437,1 +v1annealTT_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc,none,0.9011111111111111,0.009955958442154224,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1eef208fe2_2026-10-07T15-45-12.322439.json,1791387730.0107563,1 +v1annealTT_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc_norm,none,0.9011111111111111,0.009955958442154224,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1eef208fe2_2026-10-07T15-45-12.322439.json,1791387730.0107563,1 +v1annealTT_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc,none,0.8877777777777778,0.010527172059500687,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f912b5595_2026-10-07T15-53-12.417305.json,1791388217.291072,1 +v1annealTT_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc_norm,none,0.8877777777777778,0.010527172059500687,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f912b5595_2026-10-07T15-53-12.417305.json,1791388217.291072,1 +v1annealTT_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc,none,0.8988888888888888,0.010054780672527,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d3e11c32b_2026-10-07T15-44-54.922087.json,1791387719.9849205,1 +v1annealTT_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc_norm,none,0.8988888888888888,0.010054780672527,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d3e11c32b_2026-10-07T15-44-54.922087.json,1791387719.9849205,1 +v1annealTT_merge3_116k_120k,bigbench_cs_algorithms_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7674242424242425,0.011632621074299871,1320,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26c36489bc_2026-10-07T15-45-11.584245.json,1791387725.2709453,1 +v1annealTT_merge3_116k_120k,bigbench_dyck_languages_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.608,0.015445859463771295,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/78d882a93a_2026-10-07T16-11-41.936455.json,1791389323.1194706,1 +v1annealTT_merge3_116k_120k,bigbench_language_identification_multiple_choice,10,lm-eval,vllm,,acc,none,0.2535,0.004350364072897426,10000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/df2d9982d6_2026-10-07T16-42-56.834526.json,1791387727.7719357,1 +v1annealTT_merge3_116k_120k,bigbench_operators_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.8523809523809524,0.02453663059884111,210,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/65dba8ea50_2026-10-07T15-42-43.257518.json,1791387600.077442,1 +v1annealTT_merge3_116k_120k,bigbench_qa_wikidata_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7262437872151961,0.003127961185576554,20321,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/27c912a98b_2026-10-07T16-19-41.370321.json,1791389687.8060808,1 +v1annealTT_merge3_116k_120k,bigbench_repeat_copy_logic_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.6875,0.08324928557283298,32,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8435ccc8c7_2026-10-07T15-44-41.814424.json,1791387721.5862203,1 +v1annealTT_merge3_116k_120k,boolq,10,lm-eval,vllm,,acc,none,0.8697247706422019,0.005887275814052576,3270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aa6ba75c4d_2026-10-07T16-14-46.611531.json,1791389318.1775331,1 +v1annealTT_merge3_116k_120k,commonsense_qa,10,lm-eval,vllm,,acc,none,0.823914823914824,0.010904923946045652,1221,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a35b45ae0b_2026-10-07T15-49-23.159452.json,1791387966.2931771,1 +v1annealTT_merge3_116k_120k,copa,0,lm-eval,vllm,,acc,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5d41bcc57a_2026-10-07T15-38-25.690243.json,1791387345.4776843,1 +v1annealTT_merge3_116k_120k,coqa,0,lm-eval,vllm,,em,none,0.6971666666666666,0.016959700160253957,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e094da4413_2026-10-07T15-44-52.561423.json,1791387724.9988008,1 +v1annealTT_merge3_116k_120k,coqa,0,lm-eval,vllm,,f1,none,0.8231270835701946,0.012142262887597828,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e094da4413_2026-10-07T15-44-52.561423.json,1791387724.9988008,1 +v1annealTT_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.057388250233224,0.01793283346863111,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/61252e6243/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-26-15.241754.json,1791390376.097559,1 +v1annealTT_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7088401351465765,0.003948761700179071,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/61252e6243/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-26-15.241754.json,1791390376.097559,1 +v1annealTT_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.26708679906057137,0.00606223450378336,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/61252e6243/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-26-15.241754.json,1791390376.097559,1 +v1annealTT_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.08902507600656,0.011945780017464432,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/61252e6243/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-26-15.241754.json,1791390376.097559,1 +v1annealTT_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.12968106791977,0.018287954075872435,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/34f43dc127/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-28.318837.json,1791390209.1888,1 +v1annealTT_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7175348233493483,0.0037355459626408852,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/34f43dc127/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-28.318837.json,1791390209.1888,1 +v1annealTT_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28679029117072485,0.006383041367375865,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/34f43dc127/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-28.318837.json,1791390209.1888,1 +v1annealTT_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.44784835970317,0.011629202410380566,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/34f43dc127/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-28.318837.json,1791390209.1888,1 +v1annealTT_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.61841628796396,0.01814984095816146,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/dd8b750613/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-15.050152.json,1791388756.285144,1 +v1annealTT_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7057547006513905,0.003967924307371389,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/dd8b750613/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-15.050152.json,1791388756.285144,1 +v1annealTT_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.26707508685435627,0.006255144860177301,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/dd8b750613/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-15.050152.json,1791388756.285144,1 +v1annealTT_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.4688038320858,0.011529390333584882,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/dd8b750613/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-15.050152.json,1791388756.285144,1 +v1annealTT_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,49.20892559699746,0.019126751452249832,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/27b62d9405/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.229300.json,1791388870.075022,1 +v1annealTT_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7342812852988763,0.003975506843506941,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/27b62d9405/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.229300.json,1791388870.075022,1 +v1annealTT_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3217995455153656,0.0069876367205743235,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/27b62d9405/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.229300.json,1791388870.075022,1 +v1annealTT_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.49483993250541,0.012625145892980527,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/27b62d9405/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.229300.json,1791388870.075022,1 +v1annealTT_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,42.87709578419467,0.018178022223460304,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7276e092be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-03.772208.json,1791388865.145085,1 +v1annealTT_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6922510665303218,0.004140369382437186,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7276e092be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-03.772208.json,1791388865.145085,1 +v1annealTT_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.25911527524081185,0.006295343220147358,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7276e092be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-03.772208.json,1791388865.145085,1 +v1annealTT_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.8696886853922,0.012377123770009487,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7276e092be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-03.772208.json,1791388865.145085,1 +v1annealTT_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,51.6507623438335,0.01958149828171703,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b9e5da5990/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.294365.json,1791388859.321734,1 +v1annealTT_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7522860637598164,0.003910207752637425,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b9e5da5990/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.294365.json,1791388859.321734,1 +v1annealTT_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.35002611790319327,0.00700040981272893,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b9e5da5990/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.294365.json,1791388859.321734,1 +v1annealTT_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.36874940654636,0.01277257057223485,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b9e5da5990/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.294365.json,1791388859.321734,1 +v1annealTT_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.53395449495851,0.019499444188279064,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fd84d597e9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.700430.json,1791388859.555,1 +v1annealTT_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7217380479301574,0.003959319015471464,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fd84d597e9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.700430.json,1791388859.555,1 +v1annealTT_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2945453508063086,0.006732025265202957,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fd84d597e9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.700430.json,1791388859.555,1 +v1annealTT_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.61008615476206,0.012908599194599298,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fd84d597e9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.700430.json,1791388859.555,1 +v1annealTT_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.890731120897165,0.01849152318776231,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/373c739f44/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-18.859452.json,1791388760.495487,1 +v1annealTT_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6635560843238741,0.004161039092667136,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/373c739f44/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-18.859452.json,1791388760.495487,1 +v1annealTT_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22708985742592572,0.005797296221243644,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/373c739f44/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-18.859452.json,1791388760.495487,1 +v1annealTT_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.02492888051593,0.013219811770597919,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/373c739f44/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-18.859452.json,1791388760.495487,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu,none,34.606549285417444,0.015295554229754182,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d691fe31a5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-16.334540.json,1791389057.219495,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6278922836676535,0.0037753753677967866,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d691fe31a5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-16.334540.json,1791389057.219495,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.184537255427844,0.004925269153574806,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d691fe31a5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-16.334540.json,1791389057.219495,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.39228343404706,0.0106431223751229,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d691fe31a5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-16.334540.json,1791389057.219495,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu,none,31.64722317427725,0.01758724348544082,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/21c5b2234a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-39.519061.json,1791390340.319325,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5929347227172485,0.004480918156361068,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/21c5b2234a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-39.519061.json,1791390340.319325,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1598163566317503,0.004845575476361388,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/21c5b2234a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-39.519061.json,1791390340.319325,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.63438640065737,0.012371133801972084,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/21c5b2234a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-39.519061.json,1791390340.319325,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu,none,41.13836128316171,0.017641222469214183,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b373b3a2e5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-15.947187.json,1791388816.80908,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6608235799942291,0.003970074499470486,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b373b3a2e5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-15.947187.json,1791388816.80908,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.22841336541725055,0.005543963776140933,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b373b3a2e5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-15.947187.json,1791388816.80908,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,64.78141059893154,0.011664954096528702,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b373b3a2e5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-15.947187.json,1791388816.80908,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu,none,43.3584380169312,0.018000119453088295,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e53e82784d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-38.612435.json,1791389019.444094,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6726332097460765,0.0041910884998361,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e53e82784d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-38.612435.json,1791389019.444094,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.26596264530345115,0.006082577100462538,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e53e82784d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-38.612435.json,1791389019.444094,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.93051588576537,0.012884531726853108,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e53e82784d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-38.612435.json,1791389019.444094,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu,none,32.27509468739261,0.019611494766511948,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9fda6ea897/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-12.573068.json,1791388993.394909,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.586578852733555,0.004977496844849803,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9fda6ea897/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-12.573068.json,1791388993.394909,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16521107875993146,0.005554219787094458,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9fda6ea897/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-12.573068.json,1791388993.394909,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.5162743830141,0.01429117265954945,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9fda6ea897/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-12.573068.json,1791388993.394909,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu,none,48.09726031346538,0.02026667559761242,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4a359c1412/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-32.363263.json,1791388893.493709,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7104837905172632,0.004343576946486624,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4a359c1412/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-32.363263.json,1791388893.493709,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3153371412752262,0.007158525987331766,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4a359c1412/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-32.363263.json,1791388893.493709,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.08863967761012,0.012586787446260014,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4a359c1412/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-32.363263.json,1791388893.493709,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu,none,39.91150843216965,0.02156798490361194,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b547a56cb6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-52.584893.json,1791390233.678897,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6475430490544312,0.004770301933052469,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b547a56cb6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-52.584893.json,1791390233.678897,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23597562387720136,0.00658833650269115,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b547a56cb6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-52.584893.json,1791390233.678897,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.43934776053821,0.014322688675640086,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b547a56cb6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-52.584893.json,1791390233.678897,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu,none,26.82118127542296,0.01490991117395548,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bb82c246fa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-56.422487.json,1791388917.268239,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_1,none,0.5356682344444074,0.004382906311955904,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bb82c246fa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-56.422487.json,1791388917.268239,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_4,none,0.12554052025411633,0.004015120428431387,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bb82c246fa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-56.422487.json,1791388917.268239,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,chrf++,rescored,51.10743595954629,0.01247818854303487,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bb82c246fa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-56.422487.json,1791388917.268239,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu,none,26.63927767895182,0.019153646765026282,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/773f09d684/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-24-41.099173.json,1791390282.209569,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5474401230078605,0.005218847894386875,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/773f09d684/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-24-41.099173.json,1791390282.209569,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1242658130021651,0.005243886656723755,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/773f09d684/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-24-41.099173.json,1791390282.209569,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.60201734142567,0.013867428946851631,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/773f09d684/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-24-41.099173.json,1791390282.209569,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu,none,19.179750806495854,0.015817892531057493,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67b053d74b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-11.473424.json,1791388872.736935,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.488363979485125,0.004594995417777746,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67b053d74b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-11.473424.json,1791388872.736935,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.07473621015433743,0.0037383412245570063,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67b053d74b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-11.473424.json,1791388872.736935,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,52.39828872810751,0.011208709196719662,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67b053d74b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-11.473424.json,1791388872.736935,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu,none,25.30603211698625,0.01912547110056865,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/74bf2b6999/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-38.131030.json,1791388898.987889,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5242077773727616,0.0052271161490585385,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/74bf2b6999/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-38.131030.json,1791388898.987889,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11592418821339362,0.005207077045842789,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/74bf2b6999/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-38.131030.json,1791388898.987889,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.1759235461468,0.013151225566814069,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/74bf2b6999/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-38.131030.json,1791388898.987889,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu,none,50.94817770229759,0.022803318966813407,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4690dc8e80/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-24-20.302169.json,1791390261.38238,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7013217548192071,0.004867862812016135,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4690dc8e80/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-24-20.302169.json,1791390261.38238,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.36147662670312813,0.007874651525917856,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4690dc8e80/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-24-20.302169.json,1791390261.38238,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.81839300998055,0.015195470096056356,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4690dc8e80/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-24-20.302169.json,1791390261.38238,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu,none,32.25992526176672,0.018429269615904655,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/771d6f0ee4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-23.786237.json,1791388944.638213,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5897042605665977,0.0044659117959462025,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/771d6f0ee4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-23.786237.json,1791388944.638213,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16907050112546837,0.005162798083480744,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/771d6f0ee4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-23.786237.json,1791388944.638213,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.01997567036787,0.013132021586992103,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/771d6f0ee4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-23.786237.json,1791388944.638213,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu,none,37.41728247794152,0.016343464512211053,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f585d844b6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-37.603163.json,1791388898.513583,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6389400259097868,0.0038252408737966606,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f585d844b6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-37.603163.json,1791388898.513583,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2092387828308334,0.005392225933306984,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f585d844b6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-37.603163.json,1791388898.513583,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.00835427557669,0.01114354078436512,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f585d844b6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-37.603163.json,1791388898.513583,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.66931696410413,0.018750765695591726,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1002283ffd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-58.443012.json,1791388919.484989,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5780682354982501,0.005015526158091917,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1002283ffd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-58.443012.json,1791388919.484989,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16298725243085446,0.005322920613804467,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1002283ffd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-58.443012.json,1791388919.484989,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.454399608265895,0.013608684966724531,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1002283ffd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-58.443012.json,1791388919.484989,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu,none,26.677262422831106,0.018380568863235105,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cdf5a418f2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-45.175512.json,1791388786.062282,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5583300618363151,0.0044302574737668235,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cdf5a418f2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-45.175512.json,1791388786.062282,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11621290401880732,0.004539087891696903,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cdf5a418f2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-45.175512.json,1791388786.062282,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.962283596991504,0.01232818341057629,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cdf5a418f2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-45.175512.json,1791388786.062282,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu,none,28.809795694768447,0.018627480241605123,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2c968980ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-08.943809.json,1791390310.235561,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5406318698287357,0.004976669128256246,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2c968980ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-08.943809.json,1791390310.235561,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.14500126664698507,0.00544217035723241,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2c968980ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-08.943809.json,1791390310.235561,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,53.139778464995736,0.01373704501609914,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2c968980ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-08.943809.json,1791390310.235561,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu,none,32.359456644662565,0.014748277574675214,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bcda0bb536/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-37.215606.json,1791390218.227648,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5915814390535375,0.003824348657220408,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bcda0bb536/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-37.215606.json,1791390218.227648,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16451118946644142,0.004271477927343102,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bcda0bb536/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-37.215606.json,1791390218.227648,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.695080838198756,0.01014814021905936,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bcda0bb536/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-23-37.215606.json,1791390218.227648,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu,none,3.604272459648877,0.007333820798116928,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/83e8025fc5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-33-55.518042.json,1791390836.752437,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_1,none,0.21401260049413018,0.003931320659187869,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/83e8025fc5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-33-55.518042.json,1791390836.752437,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_4,none,0.006121655838951712,0.0009484612913633185,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/83e8025fc5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-33-55.518042.json,1791390836.752437,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,chrf++,rescored,26.169403903635153,0.009436821213498437,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/83e8025fc5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-33-55.518042.json,1791390836.752437,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu,none,26.701214457993807,0.019988709432755873,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/da6a9853cf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-28-20.431995.json,1791390501.314693,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.547355894555867,0.004929184483800216,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/da6a9853cf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-28-20.431995.json,1791390501.314693,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12621168550065853,0.005024374913795724,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/da6a9853cf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-28-20.431995.json,1791390501.314693,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.93432729887764,0.013115191031819238,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/da6a9853cf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-28-20.431995.json,1791390501.314693,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu,none,31.677017418698707,0.019722975814926838,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/abee10d3bc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-41.012565.json,1791388962.214257,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5906335745542494,0.005278831866980714,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/abee10d3bc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-41.012565.json,1791388962.214257,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1699217483740538,0.006220343667598994,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/abee10d3bc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-41.012565.json,1791388962.214257,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.79023392027648,0.014317251328502815,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/abee10d3bc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-41.012565.json,1791388962.214257,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu,none,36.115161770161485,0.017322213903821916,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ba7e9e018e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-28.644717.json,1791388769.834601,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6319246553217789,0.003954905998868821,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ba7e9e018e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-28.644717.json,1791388769.834601,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.1915068042041759,0.005108935563397035,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ba7e9e018e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-28.644717.json,1791388769.834601,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,61.924862796443115,0.011550247801336568,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ba7e9e018e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-28.644717.json,1791388769.834601,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu,none,40.24885083166955,0.020029263510238107,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/62bda287da/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-31.983225.json,1791388953.182038,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6523617659397832,0.0046369742365146615,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/62bda287da/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-31.983225.json,1791388953.182038,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.24119241031376135,0.006758168429621493,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/62bda287da/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-31.983225.json,1791388953.182038,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.14174901197052,0.01352592485990635,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/62bda287da/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-31.983225.json,1791388953.182038,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu,none,28.04061027642653,0.016662628867425196,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/93ba781e28/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-04.506027.json,1791388805.345156,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5751883615660695,0.004418877509237966,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/93ba781e28/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-04.506027.json,1791388805.345156,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12999141039904505,0.004642019398727056,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/93ba781e28/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-04.506027.json,1791388805.345156,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.90042530525261,0.011982142001519919,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/93ba781e28/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-04.506027.json,1791388805.345156,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu,none,34.62270521665472,0.015830100179669935,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/15e2dbef6e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-34.290869.json,1791388835.236579,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6150974067399972,0.0037626560939545044,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/15e2dbef6e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-34.290869.json,1791388835.236579,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1727349806389441,0.004542092744437821,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/15e2dbef6e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-34.290869.json,1791388835.236579,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.13266173682644,0.010994232613138352,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/15e2dbef6e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-34.290869.json,1791388835.236579,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu,none,22.808391198106282,0.015707825418342262,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/01ad02b2ff/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-04.736200.json,1791388745.570461,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.4962525449356643,0.004480683975446397,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/01ad02b2ff/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-04.736200.json,1791388745.570461,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.09721378108129085,0.003918265503707668,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/01ad02b2ff/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-04.736200.json,1791388745.570461,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,49.343769415423054,0.012009027258551387,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/01ad02b2ff/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-04.736200.json,1791388745.570461,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu,none,50.284573887177956,0.02132911854510255,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8984172129/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-22.608072.json,1791388883.908824,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7269688078799607,0.0045839228899414415,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8984172129/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-22.608072.json,1791388883.908824,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.34273290263007683,0.007733748292657695,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8984172129/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-22.608072.json,1791388883.908824,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.02110805646288,0.013723299166212762,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8984172129/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-22.608072.json,1791388883.908824,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu,none,41.37713940528671,0.018931673133161634,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ab7801ba1e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-36.998215.json,1791388778.219035,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6515965354058719,0.004489655400397619,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ab7801ba1e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-36.998215.json,1791388778.219035,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2555783025062225,0.006414388993898578,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ab7801ba1e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-36.998215.json,1791388778.219035,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.359498127520844,0.012926620261569774,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ab7801ba1e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-36.998215.json,1791388778.219035,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu,none,34.38534067537826,0.020737870319788916,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2151853c2f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-19.802713.json,1791388760.818519,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5984670096230108,0.0051141188815531655,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2151853c2f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-19.802713.json,1791388760.818519,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1918880187534822,0.006164008111966507,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2151853c2f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-19.802713.json,1791388760.818519,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.433192399990396,0.014565766810314193,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2151853c2f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-19.802713.json,1791388760.818519,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.225512423568,0.018254972598079545,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9516c22ae3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-11.173434.json,1791388992.016863,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5857737397704951,0.004916680753711107,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9516c22ae3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-11.173434.json,1791388992.016863,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16579356380806998,0.005436600715088295,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9516c22ae3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-11.173434.json,1791388992.016863,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.108823137326965,0.013588730172100829,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9516c22ae3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-11.173434.json,1791388992.016863,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu,none,29.093402201999286,0.013380458127609731,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c1a351423f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-11.566996.json,1791388873.270418,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5765005882714968,0.0035853918045326114,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c1a351423f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-11.566996.json,1791388873.270418,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.13872052722441186,0.003757758232304157,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c1a351423f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-11.566996.json,1791388873.270418,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.57650608980437,0.01006461199548952,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c1a351423f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-11.566996.json,1791388873.270418,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu,none,35.04322196356777,0.01899229474241682,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f59008628e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-25.473576.json,1791388826.861214,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6133236974667383,0.0047016700036065446,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f59008628e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-25.473576.json,1791388826.861214,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.19257976663872067,0.005656999750117983,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f59008628e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-25.473576.json,1791388826.861214,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,59.30664217206875,0.013457275313663307,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f59008628e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-25.473576.json,1791388826.861214,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu,none,46.36217332031241,0.019902418994917476,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bb735d4f3d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-33.892539.json,1791390334.968756,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6920277685646824,0.004496192163755292,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bb735d4f3d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-33.892539.json,1791390334.968756,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2960471812556275,0.0068739410475028295,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bb735d4f3d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-33.892539.json,1791390334.968756,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.63548093368222,0.013161890247050053,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bb735d4f3d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-33.892539.json,1791390334.968756,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu,none,24.899871561929352,0.01847765423325997,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0beb23f14d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-33.846748.json,1791388834.660346,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5365630516216214,0.004913060462432444,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0beb23f14d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-33.846748.json,1791388834.660346,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11392328886910225,0.004898117158788523,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0beb23f14d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-33.846748.json,1791388834.660346,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.56701800019283,0.013775043199176835,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0beb23f14d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-33.846748.json,1791388834.660346,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu,none,30.360978373988946,0.018510765666134348,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fb53f2298d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-20.121128.json,1791388941.530404,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.5599003760626245,0.004908102643731673,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fb53f2298d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-20.121128.json,1791388941.530404,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.14992753443257728,0.00504360558786058,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fb53f2298d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-20.121128.json,1791388941.530404,1 +v1annealTT_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,55.64085151802646,0.013132387205935105,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fb53f2298d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-02-20.121128.json,1791388941.530404,1 +v1annealTT_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.60400415210983,0.01836764474983154,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8e33eb7f6b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-55.220884.json,1791388856.35202,1 +v1annealTT_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6768652461414347,0.004173627453916211,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8e33eb7f6b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-55.220884.json,1791388856.35202,1 +v1annealTT_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23640268016858443,0.006261584282758079,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8e33eb7f6b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-55.220884.json,1791388856.35202,1 +v1annealTT_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.08117958750937,0.012645554361354103,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8e33eb7f6b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-55.220884.json,1791388856.35202,1 +v1annealTT_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.356442116016204,0.018407862386298168,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/248645fd5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.504719.json,1791388870.32111,1 +v1annealTT_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6264345710677722,0.004458534992474621,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/248645fd5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.504719.json,1791388870.32111,1 +v1annealTT_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18394258070733893,0.005596295706447679,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/248645fd5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.504719.json,1791388870.32111,1 +v1annealTT_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.957248697334244,0.013533195018073554,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/248645fd5b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.504719.json,1791388870.32111,1 +v1annealTT_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.425954521466466,0.018102645904359598,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5fe8d00248/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.335924.json,1791388859.426462,1 +v1annealTT_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6541877524055894,0.004248667423904233,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5fe8d00248/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.335924.json,1791388859.426462,1 +v1annealTT_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21089679139539946,0.005915141089457958,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5fe8d00248/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.335924.json,1791388859.426462,1 +v1annealTT_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.61112369001322,0.012909657261214284,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5fe8d00248/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-00-58.335924.json,1791388859.426462,1 +v1annealTT_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,47.28910043773448,0.024206288628815076,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7e87a1f8a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-50.328028.json,1791388791.899065,1 +v1annealTT_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7263264591351991,0.004345494576665797,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7e87a1f8a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-50.328028.json,1791388791.899065,1 +v1annealTT_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3141812694627571,0.007116231255152434,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7e87a1f8a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-50.328028.json,1791388791.899065,1 +v1annealTT_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.21785221286785,0.014724842013617496,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7e87a1f8a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-50.328028.json,1791388791.899065,1 +v1annealTT_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.2760738213716,0.02046932828396336,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5637ec0993/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-14.637303.json,1791388875.905713,1 +v1annealTT_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7055326252208092,0.004316377738767728,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5637ec0993/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-14.637303.json,1791388875.905713,1 +v1annealTT_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28958366346117276,0.007029818336727085,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5637ec0993/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-14.637303.json,1791388875.905713,1 +v1annealTT_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.20555266268919,0.013621444059131349,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5637ec0993/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-14.637303.json,1791388875.905713,1 +v1annealTT_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.556198067187665,0.01836589559901935,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e46bba8117/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-29.343908.json,1791389010.370067,1 +v1annealTT_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7051275082185159,0.004020229352093045,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e46bba8117/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-29.343908.json,1791389010.370067,1 +v1annealTT_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2765247784176464,0.006461680904035231,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e46bba8117/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-29.343908.json,1791389010.370067,1 +v1annealTT_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.97216549115348,0.011862378487374588,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e46bba8117/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-03-29.343908.json,1791389010.370067,1 +v1annealTT_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,41.041504561744674,0.01914736453626868,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cb4d1b7584/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-34.413238.json,1791390335.44454,1 +v1annealTT_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6767241358025979,0.004258538024313944,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cb4d1b7584/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-34.413238.json,1791390335.44454,1 +v1annealTT_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2379941398508942,0.006167499331631535,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cb4d1b7584/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-34.413238.json,1791390335.44454,1 +v1annealTT_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.24154594468526,0.013287379306756525,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cb4d1b7584/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-34.413238.json,1791390335.44454,1 +v1annealTT_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.8168806963627,0.019863545645376287,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/45b5abe85d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-48.642211.json,1791388789.661723,1 +v1annealTT_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6625663814493614,0.004243433122051056,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/45b5abe85d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-48.642211.json,1791388789.661723,1 +v1annealTT_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2198506951491567,0.005916924506139848,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/45b5abe85d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-48.642211.json,1791388789.661723,1 +v1annealTT_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.55865314476268,0.013539079077159415,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/45b5abe85d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-48.642211.json,1791388789.661723,1 +v1annealTT_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.227662533793826,0.019056464511466344,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/af0036b65c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.762095.json,1791388870.881864,1 +v1annealTT_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.656334725750463,0.004424709632012064,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/af0036b65c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.762095.json,1791388870.881864,1 +v1annealTT_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2261922398359437,0.006308726617409931,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/af0036b65c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.762095.json,1791388870.881864,1 +v1annealTT_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.62793442858735,0.013562201330822782,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/af0036b65c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.762095.json,1791388870.881864,1 +v1annealTT_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.4653088593092,0.01733452899789477,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/efb8cf9d06/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-02.940850.json,1791388744.110671,1 +v1annealTT_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6520368068163886,0.0038981094886619146,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/efb8cf9d06/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-02.940850.json,1791388744.110671,1 +v1annealTT_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.19952146183490121,0.005208086159947179,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/efb8cf9d06/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-02.940850.json,1791388744.110671,1 +v1annealTT_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.21065586198805,0.012150703304713864,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/efb8cf9d06/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-02.940850.json,1791388744.110671,1 +v1annealTT_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,20.94030673948092,0.017234481996261652,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7ce52e2485/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-36-36.495058.json,1791390997.136355,1 +v1annealTT_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5122594095368285,0.004426490851844946,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7ce52e2485/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-36-36.495058.json,1791390997.136355,1 +v1annealTT_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.0860793818893895,0.0037282416261319663,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7ce52e2485/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-36-36.495058.json,1791390997.136355,1 +v1annealTT_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,47.609590303564666,0.013210881547499881,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7ce52e2485/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-36-36.495058.json,1791390997.136355,1 +v1annealTT_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.41466983389385,0.01882937568523763,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/458e558492/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-08.110996.json,1791388749.169509,1 +v1annealTT_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6407263518343831,0.004495831959600731,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/458e558492/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-08.110996.json,1791388749.169509,1 +v1annealTT_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20994725853477259,0.0059629035428737385,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/458e558492/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-08.110996.json,1791388749.169509,1 +v1annealTT_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.602486193718505,0.013878465926777422,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/458e558492/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-08.110996.json,1791388749.169509,1 +v1annealTT_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.79021843522024,0.01943363263183268,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/80ad4ec62d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-29.743323.json,1791388890.94414,1 +v1annealTT_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6689054815295262,0.004282663579434271,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/80ad4ec62d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-29.743323.json,1791388890.94414,1 +v1annealTT_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23096827879858525,0.006248467411512493,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/80ad4ec62d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-29.743323.json,1791388890.94414,1 +v1annealTT_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.52839015148558,0.013036996036921213,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/80ad4ec62d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-29.743323.json,1791388890.94414,1 +v1annealTT_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.40317127860829,0.01884204924487271,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4288257020/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-11.078230.json,1791388751.968513,1 +v1annealTT_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7139946502716232,0.0038307758026962747,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4288257020/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-11.078230.json,1791388751.968513,1 +v1annealTT_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28716063823743926,0.006369338225233315,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4288257020/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-11.078230.json,1791388751.968513,1 +v1annealTT_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.24024256160742,0.012446448830378584,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4288257020/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-11.078230.json,1791388751.968513,1 +v1annealTT_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,58.99563958279015,0.020647289730678215,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8e75d6e853/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-09.344490.json,1791388750.430329,1 +v1annealTT_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7893057688274744,0.0037797205232142682,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8e75d6e853/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-09.344490.json,1791388750.430329,1 +v1annealTT_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.42837271669327065,0.007657658644690686,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8e75d6e853/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-09.344490.json,1791388750.430329,1 +v1annealTT_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,77.17896618134161,0.012298025772812885,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8e75d6e853/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-09.344490.json,1791388750.430329,1 +v1annealTT_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.40005954629632,0.018954414325239165,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/13026ee3c2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-01.972315.json,1791388742.79265,1 +v1annealTT_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6203628194698015,0.004368748507717808,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/13026ee3c2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-01.972315.json,1791388742.79265,1 +v1annealTT_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1821482395658935,0.0055075438103260425,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/13026ee3c2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-01.972315.json,1791388742.79265,1 +v1annealTT_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.13061590777282,0.013439893551229846,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/13026ee3c2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-01.972315.json,1791388742.79265,1 +v1annealTT_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.21788460070472,0.01855612966182743,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a9da8b1704/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-31.985790.json,1791390332.801611,1 +v1annealTT_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7056911536205622,0.003892704331710936,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a9da8b1704/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-31.985790.json,1791390332.801611,1 +v1annealTT_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2869321855939978,0.006176769363774625,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a9da8b1704/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-31.985790.json,1791390332.801611,1 +v1annealTT_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.89993962560582,0.01223131129851169,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a9da8b1704/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-25-31.985790.json,1791390332.801611,1 +v1annealTT_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.14646642219233,0.017761560739624475,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e1c0932639/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-40.059576.json,1791389080.867012,1 +v1annealTT_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6160204478251364,0.0042762154089853455,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e1c0932639/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-40.059576.json,1791389080.867012,1 +v1annealTT_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17101179214745835,0.005187998685817101,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e1c0932639/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-40.059576.json,1791389080.867012,1 +v1annealTT_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.002977625389406,0.012652005063676457,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e1c0932639/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-04-40.059576.json,1791389080.867012,1 +v1annealTT_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,52.036688309355036,0.019408495053472776,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/841a6066f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.979567.json,1791388870.984955,1 +v1annealTT_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7542234302342546,0.003979961774514585,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/841a6066f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.979567.json,1791388870.984955,1 +v1annealTT_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.35398115425776705,0.007018331487291981,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/841a6066f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.979567.json,1791388870.984955,1 +v1annealTT_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.54354500763405,0.012767178162267273,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/841a6066f9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-09.979567.json,1791388870.984955,1 +v1annealTT_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.99956619532921,0.018689182154277548,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/12059505bb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-00.819469.json,1791388861.696561,1 +v1annealTT_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7237151393438513,0.004019947658859862,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/12059505bb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-00.819469.json,1791388861.696561,1 +v1annealTT_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.30192386385382974,0.006733679937257194,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/12059505bb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-00.819469.json,1791388861.696561,1 +v1annealTT_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.31310281049802,0.012505687897162353,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/12059505bb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-00.819469.json,1791388861.696561,1 +v1annealTT_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,41.56816333330585,0.019927257712204296,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/515360ec21/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-02.443312.json,1791388863.343366,1 +v1annealTT_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6842037303321832,0.0043180019791849615,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/515360ec21/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-02.443312.json,1791388863.343366,1 +v1annealTT_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.24565996732945927,0.006439495293202172,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/515360ec21/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-02.443312.json,1791388863.343366,1 +v1annealTT_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.329256665659,0.013129390938307665,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/515360ec21/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-02.443312.json,1791388863.343366,1 +v1annealTT_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.70893835424271,0.018660994092553892,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2d097a03af/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-23.508197.json,1791388764.367777,1 +v1annealTT_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6632340945580719,0.004142818298106687,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2d097a03af/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-23.508197.json,1791388764.367777,1 +v1annealTT_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2178700855701052,0.005833755677215485,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2d097a03af/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-23.508197.json,1791388764.367777,1 +v1annealTT_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.511676082402126,0.013104610615795823,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2d097a03af/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-23.508197.json,1791388764.367777,1 +v1annealTT_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.04551574902501,0.020487615095268703,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ff305d8950/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-57.240686.json,1791388798.3986,1 +v1annealTT_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6278591445052815,0.004087281094018276,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ff305d8950/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-57.240686.json,1791388798.3986,1 +v1annealTT_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17531766457785947,0.005081517650318506,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ff305d8950/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-57.240686.json,1791388798.3986,1 +v1annealTT_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.95774159063292,0.01302157083849132,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ff305d8950/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-57.240686.json,1791388798.3986,1 +v1annealTT_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.85239626348941,0.019024998617188548,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/87de21259e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-58.468265.json,1791388799.486221,1 +v1annealTT_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7204381177455935,0.004060136185019469,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/87de21259e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-58.468265.json,1791388799.486221,1 +v1annealTT_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29609373098953834,0.0066339746346382,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/87de21259e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-58.468265.json,1791388799.486221,1 +v1annealTT_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.96623331817231,0.012309906310487,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/87de21259e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-59-58.468265.json,1791388799.486221,1 +v1annealTT_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,50.97062890677015,0.018695992425260953,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/731e092912/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-58-58.211667.json,1791388739.461703,1 +v1annealTT_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7424164865490399,0.0037862951795275854,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/731e092912/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-58-58.211667.json,1791388739.461703,1 +v1annealTT_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.33517434065393886,0.0067985003568433325,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/731e092912/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-58-58.211667.json,1791388739.461703,1 +v1annealTT_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,71.17851329910485,0.012355410124285964,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/731e092912/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-58-58.211667.json,1791388739.461703,1 +v1annealTT_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.5419635273811,0.018532246800951325,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bfb51ce1c2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-06.856286.json,1791388867.947667,1 +v1annealTT_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6756432406310149,0.004306690925619782,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bfb51ce1c2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-06.856286.json,1791388867.947667,1 +v1annealTT_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.24022269211228106,0.0064494205232262375,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bfb51ce1c2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-06.856286.json,1791388867.947667,1 +v1annealTT_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.658674264880474,0.0130364332141114,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bfb51ce1c2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-06.856286.json,1791388867.947667,1 +v1annealTT_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.04502498230665,0.019359320545600186,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a377359bfb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-36.865295.json,1791388898.073517,1 +v1annealTT_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6925938023125343,0.0041987534730936376,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a377359bfb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-36.865295.json,1791388898.073517,1 +v1annealTT_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2608540944521368,0.0064445578241822035,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a377359bfb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-36.865295.json,1791388898.073517,1 +v1annealTT_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.64916518270564,0.012998959598720985,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a377359bfb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-01-36.865295.json,1791388898.073517,1 +v1annealTT_merge3_116k_120k,global_mgsm_ca,5,lm-eval,vllm,,exact_match,flexible-extract,0.36,0.030418764025175005,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7744560dac_2026-10-07T15-38-38.758241.json,1791387348.8675113,1 +v1annealTT_merge3_116k_120k,global_mgsm_cs,5,lm-eval,vllm,,exact_match,flexible-extract,0.364,0.030491555220405572,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ca3aefc7c0_2026-10-07T15-52-59.098801.json,1791388205.8777459,1 +v1annealTT_merge3_116k_120k,global_mgsm_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.34,0.030020073605457907,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8cbaca3b86_2026-10-07T16-17-32.088118.json,1791389683.0060785,1 +v1annealTT_merge3_116k_120k,global_mgsm_el,5,lm-eval,vllm,,exact_match,flexible-extract,0.36,0.030418764025175,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/711565110b_2026-10-07T16-15-36.031064.json,1791389567.4029167,1 +v1annealTT_merge3_116k_120k,global_mgsm_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.348,0.03018656846451171,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/979a76bee4_2026-10-07T15-48-57.981879.json,1791387971.0918286,1 +v1annealTT_merge3_116k_120k,global_mgsm_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.356,0.03034368065715322,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cf0798019d_2026-10-07T16-17-34.615905.json,1791389688.7020485,1 +v1annealTT_merge3_116k_120k,global_mgsm_eu,5,lm-eval,vllm,,exact_match,flexible-extract,0.3,0.029040893477575856,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ce20b4d957_2026-10-07T15-53-23.861781.json,1791388219.6207058,1 +v1annealTT_merge3_116k_120k,global_mgsm_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.36,0.030418764025175005,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b829af3e43_2026-10-07T15-42-47.177103.json,1791387600.1193295,1 +v1annealTT_merge3_116k_120k,global_mgsm_gl,5,lm-eval,vllm,,exact_match,flexible-extract,0.348,0.030186568464511714,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/30fb150908_2026-10-07T16-11-31.868956.json,1791389326.158807,1 +v1annealTT_merge3_116k_120k,global_mgsm_hu,5,lm-eval,vllm,,exact_match,flexible-extract,0.344,0.03010450339231639,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6d5dea923e_2026-10-07T15-52-55.558850.json,1791388207.0430694,1 +v1annealTT_merge3_116k_120k,global_mgsm_sr,5,lm-eval,vllm,,exact_match,flexible-extract,0.364,0.03049155522040557,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c8967d9cbe_2026-10-07T15-42-48.549501.json,1791387594.500535,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs,5,lm-eval,vllm,yes,acc,none,0.6884346959122633,0.003735874522002305,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_abstract_algebra,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_anatomy,5,lm-eval,vllm,,acc,none,0.5851851851851851,0.04256193767901412,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_astronomy,5,lm-eval,vllm,,acc,none,0.8157894736842105,0.031546980450822305,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7018867924528301,0.028152837942493784,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_college_biology,5,lm-eval,vllm,,acc,none,0.8194444444444444,0.03216600808802272,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_college_medicine,5,lm-eval,vllm,,acc,none,0.6936416184971098,0.035149425512674394,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_college_physics,5,lm-eval,vllm,,acc,none,0.5392156862745098,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7702127659574468,0.0275017529444124,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7034482758620689,0.03806142687309988,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.656084656084656,0.0244644266255964,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_formal_logic,5,lm-eval,vllm,,acc,none,0.5952380952380952,0.043902592653775656,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_biology,5,lm-eval,vllm,,acc,none,0.8258064516129032,0.02157624818451461,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6403940886699507,0.0337645824650957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.030117688929503603,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_geography,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026552207828215258,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7717948717948718,0.02127839386358626,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5185185185185185,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8109243697478992,0.025435119438105305,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_physics,5,lm-eval,vllm,,acc,none,0.5827814569536424,0.040261414976346124,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8605504587155963,0.014852421490033118,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.0314155462940254,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8523206751054853,0.023094329582595715,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_human_aging,5,lm-eval,vllm,,acc,none,0.7399103139013453,0.029442495585857424,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_humanities,5,lm-eval,vllm,yes,acc,none,0.6242295430393199,0.006703605972510544,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_jurisprudence,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.040774947092526284,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7607361963190185,0.033519538795212675,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_machine_learning,5,lm-eval,vllm,,acc,none,0.5892857142857143,0.04669510663875191,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_marketing,5,lm-eval,vllm,,acc,none,0.8717948717948718,0.021901905115073377,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_miscellaneous,5,lm-eval,vllm,,acc,none,0.7969348659003831,0.014385525076611661,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_moral_disputes,5,lm-eval,vllm,,acc,none,0.7427745664739884,0.02353292543104432,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4569832402234637,0.016660498580509216,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_nutrition,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.02428861946604616,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_other,5,lm-eval,vllm,yes,acc,none,0.7087222401029932,0.007871903566488012,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_philosophy,5,lm-eval,vllm,,acc,none,0.7331189710610932,0.0251226376088166,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_prehistory,5,lm-eval,vllm,,acc,none,0.7839506172839507,0.02289916291844576,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_professional_accounting,5,lm-eval,vllm,,acc,none,0.49645390070921985,0.029826749153280853,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_professional_law,5,lm-eval,vllm,,acc,none,0.4954367666232073,0.012769704263117502,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_professional_medicine,5,lm-eval,vllm,,acc,none,0.6875,0.02815637344037142,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_professional_psychology,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.018054027458815132,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_public_relations,5,lm-eval,vllm,,acc,none,0.6363636363636364,0.04607582090719978,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7884302892427689,0.007243002247301327,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_stem,5,lm-eval,vllm,yes,acc,none,0.6666666666666666,0.00816199417182125,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_cs_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b66d6fcce1_2026-10-07T15-45-10.459184.json,1791387587.2970476,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de,5,lm-eval,vllm,yes,acc,none,0.6860846033328586,0.003746369905010054,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_abstract_algebra,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_anatomy,5,lm-eval,vllm,,acc,none,0.5851851851851851,0.04256193767901412,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.720754716981132,0.027611163402399694,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_college_mathematics,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_college_medicine,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.03435568056047877,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_college_physics,5,lm-eval,vllm,,acc,none,0.5490196078431373,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7489361702127659,0.02834696377716252,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_econometrics,5,lm-eval,vllm,,acc,none,0.5526315789473685,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7241379310344828,0.037245636197746325,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.02467786284133279,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_formal_logic,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.043435254289490965,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_biology,5,lm-eval,vllm,,acc,none,0.867741935483871,0.019272015434846444,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6798029556650246,0.032826493853041455,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8242424242424242,0.029720943006224455,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_geography,5,lm-eval,vllm,,acc,none,0.8737373737373737,0.023664359402880177,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.927461139896373,0.018718998520678213,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7307692307692307,0.022489389793654804,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5148148148148148,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.819327731092437,0.02499196496660074,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_physics,5,lm-eval,vllm,,acc,none,0.5827814569536424,0.040261414976346124,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8660550458715597,0.014602811435592633,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03214952147802747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8016877637130801,0.02595502084162111,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_human_aging,5,lm-eval,vllm,,acc,none,0.6547085201793722,0.03191100192835789,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_human_sexuality,5,lm-eval,vllm,,acc,none,0.8091603053435115,0.03446513350752599,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_humanities,5,lm-eval,vllm,yes,acc,none,0.6159404888416579,0.006752845054762855,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_jurisprudence,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.0437331304091476,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7607361963190185,0.033519538795212675,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_machine_learning,5,lm-eval,vllm,,acc,none,0.5982142857142857,0.04653333146973646,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_management,5,lm-eval,vllm,,acc,none,0.8349514563106796,0.03675668832233187,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_marketing,5,lm-eval,vllm,,acc,none,0.8803418803418803,0.021262719400406926,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_medical_genetics,5,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_miscellaneous,5,lm-eval,vllm,,acc,none,0.789272030651341,0.01458381246586261,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_moral_disputes,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.02378620325550823,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4134078212290503,0.016469814928406167,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_other,5,lm-eval,vllm,yes,acc,none,0.7061474090762794,0.007917292077736702,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_prehistory,5,lm-eval,vllm,,acc,none,0.7561728395061729,0.023891879541959576,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_professional_accounting,5,lm-eval,vllm,,acc,none,0.524822695035461,0.0297907192438297,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_professional_law,5,lm-eval,vllm,,acc,none,0.5176010430247718,0.012762321298823471,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_professional_medicine,5,lm-eval,vllm,,acc,none,0.6764705882352942,0.028418208619406728,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_professional_psychology,5,lm-eval,vllm,,acc,none,0.7369281045751634,0.01781267654232072,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_security_studies,5,lm-eval,vllm,,acc,none,0.726530612244898,0.028535560337128486,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7900552486187845,0.007202703391386886,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_sociology,5,lm-eval,vllm,,acc,none,0.845771144278607,0.025538433368578303,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_stem,5,lm-eval,vllm,yes,acc,none,0.6695210910244211,0.00815824429524707,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_de_world_religions,5,lm-eval,vllm,,acc,none,0.8304093567251462,0.02878210810540169,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b99ce4dadf_2026-10-07T15-51-54.018180.json,1791387971.731107,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el,5,lm-eval,vllm,yes,acc,none,0.670203674690215,0.0038002470198408105,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_abstract_algebra,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_anatomy,5,lm-eval,vllm,,acc,none,0.5333333333333333,0.043097329010363616,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_astronomy,5,lm-eval,vllm,,acc,none,0.8223684210526315,0.03110318238312337,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.720754716981132,0.027611163402399694,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_college_biology,5,lm-eval,vllm,,acc,none,0.7291666666666666,0.03716177437566019,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_college_chemistry,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_college_computer_science,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_college_mathematics,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_college_medicine,5,lm-eval,vllm,,acc,none,0.6994219653179191,0.03496101481191176,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_college_physics,5,lm-eval,vllm,,acc,none,0.5294117647058824,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_conceptual_physics,5,lm-eval,vllm,,acc,none,0.774468085106383,0.02732107841738755,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_econometrics,5,lm-eval,vllm,,acc,none,0.5350877192982456,0.04692008381368906,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6896551724137931,0.03855289616378948,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.024552292209342713,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_biology,5,lm-eval,vllm,,acc,none,0.8290322580645161,0.021417242936321575,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6403940886699507,0.0337645824650957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8242424242424242,0.029720943006224455,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_geography,5,lm-eval,vllm,,acc,none,0.8232323232323232,0.027178752639044908,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8808290155440415,0.02338193534812143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7538461538461538,0.02184086699042312,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48148148148148145,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8067226890756303,0.02564947026588922,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_physics,5,lm-eval,vllm,,acc,none,0.5629139072847682,0.040500357222306375,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8348623853211009,0.015919557829976096,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7083333333333334,0.030998666304560565,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8396624472573839,0.02388438092596563,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_human_aging,5,lm-eval,vllm,,acc,none,0.695067264573991,0.03089861088247754,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_human_sexuality,5,lm-eval,vllm,,acc,none,0.7251908396946565,0.03915345408847834,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_humanities,5,lm-eval,vllm,yes,acc,none,0.6097768331562168,0.006741552722883131,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_jurisprudence,5,lm-eval,vllm,,acc,none,0.8148148148148148,0.03755265865037181,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7361963190184049,0.03462419931615622,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_machine_learning,5,lm-eval,vllm,,acc,none,0.5892857142857143,0.04669510663875191,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_marketing,5,lm-eval,vllm,,acc,none,0.8162393162393162,0.0253721396717229,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_medical_genetics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_miscellaneous,5,lm-eval,vllm,,acc,none,0.7381864623243933,0.01572083867844512,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4212290502793296,0.016513676031179602,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_nutrition,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.025360603796242578,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_other,5,lm-eval,vllm,yes,acc,none,0.6813646604441583,0.008155099591957952,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_philosophy,5,lm-eval,vllm,,acc,none,0.7459807073954984,0.024723861504771655,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_prehistory,5,lm-eval,vllm,,acc,none,0.7283950617283951,0.024748624490537455,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_professional_accounting,5,lm-eval,vllm,,acc,none,0.4716312056737589,0.029779450957303062,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_professional_law,5,lm-eval,vllm,,acc,none,0.49022164276401564,0.012767793787729296,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_professional_medicine,5,lm-eval,vllm,,acc,none,0.6911764705882353,0.028064998167040053,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_professional_psychology,5,lm-eval,vllm,,acc,none,0.684640522875817,0.01879808628488684,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7705557361065973,0.007454032573831474,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_stem,5,lm-eval,vllm,yes,acc,none,0.6514430700919759,0.008230650604708758,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_el_world_religions,5,lm-eval,vllm,,acc,none,0.7953216374269005,0.03094445977853322,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfa92a933f_2026-10-07T15-48-38.722342.json,1791387722.49953,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en,5,lm-eval,vllm,yes,acc,none,0.7352941176470589,0.0035653470537944745,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_abstract_algebra,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_anatomy,5,lm-eval,vllm,,acc,none,0.674074074074074,0.040491220417025006,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_astronomy,5,lm-eval,vllm,,acc,none,0.8289473684210527,0.03064360707167711,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_business_ethics,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7660377358490567,0.02605529690115286,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_college_biology,5,lm-eval,vllm,,acc,none,0.8402777777777778,0.030635578972093305,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_college_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_college_medicine,5,lm-eval,vllm,,acc,none,0.7398843930635838,0.03345036916788986,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_college_physics,5,lm-eval,vllm,,acc,none,0.6078431372549019,0.04858083574266346,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_computer_security,5,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7872340425531915,0.02675439134803978,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_econometrics,5,lm-eval,vllm,,acc,none,0.6228070175438597,0.0455952214195822,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7448275862068966,0.03632984052707841,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.716931216931217,0.023201392938194967,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_formal_logic,5,lm-eval,vllm,,acc,none,0.6984126984126984,0.04104947269903394,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_global_facts,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_biology,5,lm-eval,vllm,,acc,none,0.8838709677419355,0.01822575794943229,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.7044334975369458,0.03210494433751457,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8363636363636363,0.028887872395487978,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_geography,5,lm-eval,vllm,,acc,none,0.8737373737373737,0.023664359402880177,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9533678756476683,0.015216761819262604,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.782051282051282,0.020932445774463234,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5370370370370371,0.030401786406101534,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.9117647058823529,0.018424189175962204,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_physics,5,lm-eval,vllm,,acc,none,0.609271523178808,0.039837983066598075,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_psychology,5,lm-eval,vllm,,acc,none,0.9100917431192661,0.012264304540230489,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7175925925925926,0.03070137211151092,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8676470588235294,0.02378429752091887,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8734177215189873,0.021644195727955198,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_human_aging,5,lm-eval,vllm,,acc,none,0.7668161434977578,0.02838039114709467,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_human_sexuality,5,lm-eval,vllm,,acc,none,0.8244274809160306,0.03336820338476075,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_humanities,5,lm-eval,vllm,yes,acc,none,0.6811902231668437,0.006502870749569112,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_international_law,5,lm-eval,vllm,,acc,none,0.859504132231405,0.03172233426002156,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_jurisprudence,5,lm-eval,vllm,,acc,none,0.8240740740740741,0.036809181416738786,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7975460122699386,0.031570650789119054,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_machine_learning,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.045479609997643805,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_management,5,lm-eval,vllm,,acc,none,0.8349514563106796,0.03675668832233187,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_marketing,5,lm-eval,vllm,,acc,none,0.8760683760683761,0.021586494001281407,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_medical_genetics,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_miscellaneous,5,lm-eval,vllm,,acc,none,0.8378033205619413,0.01318222261672081,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_moral_disputes,5,lm-eval,vllm,,acc,none,0.7947976878612717,0.021742519835276364,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5139664804469274,0.016715976410744602,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_nutrition,5,lm-eval,vllm,,acc,none,0.7581699346405228,0.024518195641879306,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_other,5,lm-eval,vllm,yes,acc,none,0.7502413904087544,0.007526669562792536,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_philosophy,5,lm-eval,vllm,,acc,none,0.7620578778135049,0.02418515064781868,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_prehistory,5,lm-eval,vllm,,acc,none,0.8209876543209876,0.02133086876212711,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_professional_accounting,5,lm-eval,vllm,,acc,none,0.549645390070922,0.029680105565029025,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_professional_law,5,lm-eval,vllm,,acc,none,0.5775749674054759,0.012615600475735015,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_professional_medicine,5,lm-eval,vllm,,acc,none,0.7389705882352942,0.026679252270103055,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_professional_psychology,5,lm-eval,vllm,,acc,none,0.7794117647058824,0.01677467236546851,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_security_studies,5,lm-eval,vllm,,acc,none,0.7551020408163265,0.02752963744017492,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8332791680207995,0.006562508937679542,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_sociology,5,lm-eval,vllm,,acc,none,0.9104477611940298,0.020190670535027884,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_stem,5,lm-eval,vllm,yes,acc,none,0.7056771328893118,0.007869895939495854,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_virology,5,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_en_world_religions,5,lm-eval,vllm,,acc,none,0.8654970760233918,0.02616822134466232,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05aa4e2882_2026-10-07T15-47-22.757652.json,1791387721.9812417,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es,5,lm-eval,vllm,yes,acc,none,0.7025352513886911,0.003686289186807658,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_abstract_algebra,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_astronomy,5,lm-eval,vllm,,acc,none,0.8289473684210527,0.03064360707167711,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7396226415094339,0.027008766090708045,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_college_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_college_medicine,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.033687629322594316,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7702127659574468,0.0275017529444124,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_econometrics,5,lm-eval,vllm,,acc,none,0.5789473684210527,0.04644602091222323,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7103448275862069,0.03780019230438011,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6798941798941799,0.024026846392873506,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_formal_logic,5,lm-eval,vllm,,acc,none,0.6825396825396826,0.04163453031302857,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_global_facts,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_biology,5,lm-eval,vllm,,acc,none,0.8548387096774194,0.020039563628053293,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.7093596059113301,0.031947400722655415,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8363636363636363,0.028887872395487978,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_geography,5,lm-eval,vllm,,acc,none,0.8686868686868687,0.02406315641682249,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7692307692307693,0.0213620277252227,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4925925925925926,0.03048219239519157,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.023005459446673992,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_physics,5,lm-eval,vllm,,acc,none,0.5827814569536424,0.040261414976346124,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8605504587155963,0.014852421490033118,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7083333333333334,0.030998666304560565,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8312236286919831,0.02438140683258622,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_human_aging,5,lm-eval,vllm,,acc,none,0.7443946188340808,0.029275891003969906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_humanities,5,lm-eval,vllm,yes,acc,none,0.6361317747077577,0.006688893579472263,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_jurisprudence,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.038935425188248496,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7423312883435583,0.03436150827846915,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_machine_learning,5,lm-eval,vllm,,acc,none,0.6160714285714286,0.04616143075028549,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_medical_genetics,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_miscellaneous,5,lm-eval,vllm,,acc,none,0.8326947637292464,0.013347327202920329,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_moral_disputes,5,lm-eval,vllm,,acc,none,0.7456647398843931,0.02344582627654551,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_moral_scenarios,5,lm-eval,vllm,,acc,none,0.47374301675977654,0.016699427672784813,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_nutrition,5,lm-eval,vllm,,acc,none,0.7581699346405228,0.024518195641879306,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_other,5,lm-eval,vllm,yes,acc,none,0.7312520115867396,0.0076857511988897,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_philosophy,5,lm-eval,vllm,,acc,none,0.752411575562701,0.024513879973621984,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_prehistory,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.02346842983245111,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_professional_accounting,5,lm-eval,vllm,,acc,none,0.5106382978723404,0.029820747191422466,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_professional_law,5,lm-eval,vllm,,acc,none,0.5123859191655802,0.012766317315473681,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_professional_medicine,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.026799562024887664,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_professional_psychology,5,lm-eval,vllm,,acc,none,0.7369281045751634,0.01781267654232072,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_security_studies,5,lm-eval,vllm,,acc,none,0.8122448979591836,0.025000256039546167,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8020799480013,0.007073697564754344,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_sociology,5,lm-eval,vllm,,acc,none,0.8407960199004975,0.025870646766169153,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_stem,5,lm-eval,vllm,yes,acc,none,0.6761814145258483,0.008054513106410024,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.91,0.028762349126466136,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_es_world_religions,5,lm-eval,vllm,,acc,none,0.8538011695906432,0.02709729011807083,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a3088875c8_2026-10-07T15-53-47.037939.json,1791388088.4217558,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr,5,lm-eval,vllm,yes,acc,none,0.6883634809856146,0.003696935427853617,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_anatomy,5,lm-eval,vllm,,acc,none,0.5851851851851851,0.04256193767901412,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_astronomy,5,lm-eval,vllm,,acc,none,0.8355263157894737,0.030167533468632726,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_business_ethics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7396226415094339,0.027008766090708045,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_college_biology,5,lm-eval,vllm,,acc,none,0.8194444444444444,0.03216600808802272,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_college_computer_science,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_college_medicine,5,lm-eval,vllm,,acc,none,0.7687861271676301,0.032147373020294655,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_college_physics,5,lm-eval,vllm,,acc,none,0.5490196078431373,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7531914893617021,0.02818544130123409,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7103448275862069,0.03780019230438011,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6613756613756614,0.024373197867983004,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_formal_logic,5,lm-eval,vllm,,acc,none,0.626984126984127,0.043255060420170875,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8483870967741935,0.020402616654416734,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6896551724137931,0.032550867699700996,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9326424870466321,0.01808839383907894,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7615384615384615,0.021606294494647772,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5148148148148148,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.819327731092437,0.02499196496660074,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_physics,5,lm-eval,vllm,,acc,none,0.6158940397350994,0.03971301814719192,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8422018348623853,0.015630022970092496,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.0314155462940254,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8578431372549019,0.024509803921568627,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8649789029535865,0.022245776632003705,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_human_sexuality,5,lm-eval,vllm,,acc,none,0.8091603053435115,0.03446513350752599,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_humanities,5,lm-eval,vllm,yes,acc,none,0.6114771519659936,0.006568141560641148,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.03957835471980979,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7361963190184049,0.03462419931615622,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_machine_learning,5,lm-eval,vllm,,acc,none,0.6339285714285714,0.04572372358737434,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_management,5,lm-eval,vllm,,acc,none,0.8252427184466019,0.03760178006026618,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_marketing,5,lm-eval,vllm,,acc,none,0.8418803418803419,0.02390232554956044,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7931034482758621,0.014485656041669067,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7572254335260116,0.02308365858698422,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3318435754189944,0.015748421208187313,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_nutrition,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.025360603796242578,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_other,5,lm-eval,vllm,yes,acc,none,0.7164467331831349,0.007830163075987943,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_prehistory,5,lm-eval,vllm,,acc,none,0.7932098765432098,0.022535006705942877,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_professional_accounting,5,lm-eval,vllm,,acc,none,0.4787234042553192,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_professional_law,5,lm-eval,vllm,,acc,none,0.5110821382007823,0.012767098998525846,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_professional_medicine,5,lm-eval,vllm,,acc,none,0.7242647058823529,0.02714627193662515,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_professional_psychology,5,lm-eval,vllm,,acc,none,0.7156862745098039,0.01824902441120767,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_public_relations,5,lm-eval,vllm,,acc,none,0.7272727272727273,0.04265792110940591,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.788755281117972,0.007242972515735087,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_stem,5,lm-eval,vllm,yes,acc,none,0.6774500475737393,0.00809449328311668,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_virology,5,lm-eval,vllm,,acc,none,0.5240963855421686,0.03887971849597267,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_fr_world_religions,5,lm-eval,vllm,,acc,none,0.8304093567251462,0.02878210810540169,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00d5b263af_2026-10-07T16-24-43.249847.json,1791389924.7033958,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it,5,lm-eval,vllm,yes,acc,none,0.6974789915966386,0.0037047904121841955,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_abstract_algebra,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_anatomy,5,lm-eval,vllm,,acc,none,0.6,0.0423207369515159,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_astronomy,5,lm-eval,vllm,,acc,none,0.8223684210526315,0.03110318238312337,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_business_ethics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7169811320754716,0.027724236492700883,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_college_mathematics,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_college_medicine,5,lm-eval,vllm,,acc,none,0.7283236994219653,0.03391750322321658,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_college_physics,5,lm-eval,vllm,,acc,none,0.5588235294117647,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_computer_security,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7531914893617021,0.02818544130123409,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7241379310344828,0.037245636197746325,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.656084656084656,0.0244644266255964,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_global_facts,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_biology,5,lm-eval,vllm,,acc,none,0.8838709677419355,0.01822575794943229,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6699507389162561,0.033085304262282594,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_geography,5,lm-eval,vllm,,acc,none,0.8686868686868687,0.02406315641682249,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7615384615384615,0.021606294494647772,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5037037037037037,0.030484701665084428,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.819327731092437,0.02499196496660074,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_physics,5,lm-eval,vllm,,acc,none,0.5695364238410596,0.04042809961395634,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8880733944954129,0.013517352714958736,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6712962962962963,0.03203614084670054,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8382352941176471,0.025845017986926906,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_human_aging,5,lm-eval,vllm,,acc,none,0.7174887892376681,0.030216831011508755,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_humanities,5,lm-eval,vllm,yes,acc,none,0.6308182784272051,0.0067085741025101,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_jurisprudence,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.038935425188248496,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7914110429447853,0.03192193448934723,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_machine_learning,5,lm-eval,vllm,,acc,none,0.6071428571428571,0.04635550135609972,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_management,5,lm-eval,vllm,,acc,none,0.7961165048543689,0.0398913985953177,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_marketing,5,lm-eval,vllm,,acc,none,0.8418803418803419,0.02390232554956044,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_medical_genetics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_miscellaneous,5,lm-eval,vllm,,acc,none,0.8186462324393359,0.01377869377846414,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_moral_disputes,5,lm-eval,vllm,,acc,none,0.7514450867052023,0.02326752843210016,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4659217877094972,0.016683615837486936,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_nutrition,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.024630048979824716,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_other,5,lm-eval,vllm,yes,acc,none,0.7215963952365626,0.007783329497558771,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_philosophy,5,lm-eval,vllm,,acc,none,0.707395498392283,0.02583989833487794,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_prehistory,5,lm-eval,vllm,,acc,none,0.7623456790123457,0.023683591837008515,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_professional_accounting,5,lm-eval,vllm,,acc,none,0.49645390070921985,0.029826749153280853,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_professional_law,5,lm-eval,vllm,,acc,none,0.5104302477183833,0.012767457253930452,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_professional_medicine,5,lm-eval,vllm,,acc,none,0.7242647058823529,0.02714627193662515,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_professional_psychology,5,lm-eval,vllm,,acc,none,0.738562091503268,0.017776947157528172,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8007799805004875,0.007065790888267817,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_sociology,5,lm-eval,vllm,,acc,none,0.8756218905472637,0.023335401790166316,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_stem,5,lm-eval,vllm,yes,acc,none,0.6723755153821757,0.008101970970832359,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_virology,5,lm-eval,vllm,,acc,none,0.5421686746987951,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_it_world_religions,5,lm-eval,vllm,,acc,none,0.8304093567251462,0.02878210810540169,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b9d286d66_2026-10-07T15-51-42.694586.json,1791387959.0350566,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt,5,lm-eval,vllm,yes,acc,none,0.6615154536390827,0.0037934687975594286,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_anatomy,5,lm-eval,vllm,,acc,none,0.6,0.0423207369515159,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_astronomy,5,lm-eval,vllm,,acc,none,0.8289473684210527,0.03064360707167711,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_business_ethics,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7169811320754716,0.027724236492700883,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_college_biology,5,lm-eval,vllm,,acc,none,0.75,0.03621034121889507,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_college_chemistry,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_college_mathematics,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_college_medicine,5,lm-eval,vllm,,acc,none,0.6936416184971098,0.035149425512674394,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_computer_security,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7446808510638298,0.0285048564705142,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_econometrics,5,lm-eval,vllm,,acc,none,0.5964912280701754,0.04615186962583705,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6587301587301587,0.024419234966819043,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8096774193548387,0.02233170761182313,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8535353535353535,0.025190921114603887,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7307692307692307,0.022489389793654804,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4777777777777778,0.030455413985678415,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7899159663865546,0.026461398717471864,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_physics,5,lm-eval,vllm,,acc,none,0.5562913907284768,0.04056527902281736,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8513761467889909,0.0152512537736609,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.0314155462940254,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7941176470588235,0.028379449451588684,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8059071729957806,0.025744902532290916,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_human_aging,5,lm-eval,vllm,,acc,none,0.7040358744394619,0.03063659134869978,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_humanities,5,lm-eval,vllm,yes,acc,none,0.581509032943677,0.006748826629844611,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_international_law,5,lm-eval,vllm,,acc,none,0.8099173553719008,0.03581796951709283,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6809815950920245,0.03661997551073836,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_machine_learning,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_marketing,5,lm-eval,vllm,,acc,none,0.8376068376068376,0.024161618127987734,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_medical_genetics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7547892720306514,0.01538435228454386,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_moral_disputes,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.024946792225272324,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3217877094972067,0.015624236160792603,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_other,5,lm-eval,vllm,yes,acc,none,0.682330222079176,0.008093944689360361,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_prehistory,5,lm-eval,vllm,,acc,none,0.7283950617283951,0.024748624490537455,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_professional_accounting,5,lm-eval,vllm,,acc,none,0.43617021276595747,0.02958345203628408,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_professional_law,5,lm-eval,vllm,,acc,none,0.4921773142112125,0.012768673076111898,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6985294117647058,0.027875982114273147,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_professional_psychology,5,lm-eval,vllm,,acc,none,0.6993464052287581,0.01855063450295291,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.777705557361066,0.007392144344486013,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_sociology,5,lm-eval,vllm,,acc,none,0.8507462686567164,0.02519692987482706,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_stem,5,lm-eval,vllm,yes,acc,none,0.6470028544243578,0.008267109654916735,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_lt_world_religions,5,lm-eval,vllm,,acc,none,0.8187134502923976,0.02954774168764006,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d058add09_2026-10-07T15-39-25.481200.json,1791387226.0718226,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl,5,lm-eval,vllm,yes,acc,none,0.6966244124768551,0.0037234426151112653,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_astronomy,5,lm-eval,vllm,,acc,none,0.8355263157894737,0.030167533468632726,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_business_ethics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7471698113207547,0.02674989977124118,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_college_medicine,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.03414014007044037,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_college_physics,5,lm-eval,vllm,,acc,none,0.5294117647058824,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7574468085106383,0.02802022627120023,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_econometrics,5,lm-eval,vllm,,acc,none,0.5701754385964912,0.04657047260594963,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7448275862068966,0.03632984052707841,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6904761904761905,0.02380952380952381,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_formal_logic,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.043435254289490965,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8516129032258064,0.02022273755433042,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6748768472906403,0.03295797566311267,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8363636363636363,0.028887872395487978,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8636363636363636,0.02445015597318985,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9326424870466321,0.01808839383907894,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7666666666666667,0.021444547301560507,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5148148148148148,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.819327731092437,0.02499196496660074,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_physics,5,lm-eval,vllm,,acc,none,0.5960264900662252,0.04006485685365344,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8770642201834863,0.014078467983673335,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.030546745264953202,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026156867523931024,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8607594936708861,0.022535526352692684,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_human_sexuality,5,lm-eval,vllm,,acc,none,0.732824427480916,0.03880848301082397,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_humanities,5,lm-eval,vllm,yes,acc,none,0.6384697130712008,0.00669880743497515,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_international_law,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.03520893951097652,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_jurisprudence,5,lm-eval,vllm,,acc,none,0.8055555555555556,0.038260763248848646,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.754601226993865,0.033809398139433525,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_machine_learning,5,lm-eval,vllm,,acc,none,0.6160714285714286,0.04616143075028549,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_marketing,5,lm-eval,vllm,,acc,none,0.8632478632478633,0.022509033937077844,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7662835249042146,0.015133383278988898,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7485549132947977,0.023357365785874006,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5039106145251396,0.016721990073156705,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_nutrition,5,lm-eval,vllm,,acc,none,0.7516339869281046,0.02473998135511354,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_other,5,lm-eval,vllm,yes,acc,none,0.7048599935629224,0.00793449006043526,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_philosophy,5,lm-eval,vllm,,acc,none,0.7363344051446945,0.02502553850053229,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_prehistory,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.023132376234543416,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_professional_accounting,5,lm-eval,vllm,,acc,none,0.48226950354609927,0.02980873964223769,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_professional_law,5,lm-eval,vllm,,acc,none,0.5071707953063885,0.012768922739553434,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6875,0.02815637344037142,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_professional_psychology,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.018120224251484508,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7949301267468313,0.0071370921033891135,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_sociology,5,lm-eval,vllm,,acc,none,0.8407960199004975,0.025870646766169153,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_stem,5,lm-eval,vllm,yes,acc,none,0.6793529971455756,0.008087650038013375,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_nl_world_religions,5,lm-eval,vllm,,acc,none,0.7953216374269005,0.03094445977853322,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac16f04fd8_2026-10-07T16-00-11.397332.json,1791388460.791452,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl,5,lm-eval,vllm,yes,acc,none,0.6801737644210226,0.003762354999614363,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_anatomy,5,lm-eval,vllm,,acc,none,0.5333333333333333,0.043097329010363616,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_astronomy,5,lm-eval,vllm,,acc,none,0.8289473684210527,0.03064360707167711,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_business_ethics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.690566037735849,0.028450154794118682,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_college_computer_science,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_college_medicine,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.03414014007044037,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7446808510638298,0.0285048564705142,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6825396825396826,0.02397386199899207,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_formal_logic,5,lm-eval,vllm,,acc,none,0.5793650793650794,0.044154382267437474,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8516129032258064,0.02022273755433042,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6798029556650246,0.032826493853041455,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8545454545454545,0.02753019635506653,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8232323232323232,0.027178752639044908,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8756476683937824,0.02381447708659357,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7615384615384615,0.021606294494647772,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5185185185185185,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8568807339449541,0.015014462497168531,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8382352941176471,0.025845017986926906,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8607594936708861,0.022535526352692684,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_human_aging,5,lm-eval,vllm,,acc,none,0.6771300448430493,0.031381476375754995,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_humanities,5,lm-eval,vllm,yes,acc,none,0.6138150903294368,0.006742722658763391,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7607361963190185,0.033519538795212675,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_marketing,5,lm-eval,vllm,,acc,none,0.8504273504273504,0.023365051491753757,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_medical_genetics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7739463601532567,0.014957458504335842,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4569832402234637,0.016660498580509216,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_nutrition,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.024630048979824716,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_other,5,lm-eval,vllm,yes,acc,none,0.6968136466044416,0.008007343279907623,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_philosophy,5,lm-eval,vllm,,acc,none,0.684887459807074,0.026385273703464482,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_prehistory,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.025171041915309698,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_professional_accounting,5,lm-eval,vllm,,acc,none,0.4787234042553192,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_professional_law,5,lm-eval,vllm,,acc,none,0.48435462842242505,0.012763982838120936,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6764705882352942,0.028418208619406728,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_professional_psychology,5,lm-eval,vllm,,acc,none,0.7205882352941176,0.018152871051538712,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_public_relations,5,lm-eval,vllm,,acc,none,0.6454545454545455,0.04582004841505413,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_security_studies,5,lm-eval,vllm,,acc,none,0.7877551020408163,0.026176967197866795,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7825804354891128,0.00729648794357377,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_sociology,5,lm-eval,vllm,,acc,none,0.8557213930348259,0.024845753212306015,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_stem,5,lm-eval,vllm,yes,acc,none,0.6628607675229939,0.008158099948767143,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pl_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99f8f53841_2026-10-07T16-14-17.576195.json,1791389316.947488,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt,5,lm-eval,vllm,yes,acc,none,0.6958410482837203,0.0037194469595915334,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_astronomy,5,lm-eval,vllm,,acc,none,0.8289473684210527,0.03064360707167711,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_business_ethics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.720754716981132,0.027611163402399694,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_college_biology,5,lm-eval,vllm,,acc,none,0.8125,0.032639560491693344,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_college_computer_science,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_college_medicine,5,lm-eval,vllm,,acc,none,0.7572254335260116,0.03269263806141769,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_computer_security,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7574468085106383,0.02802022627120023,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_econometrics,5,lm-eval,vllm,,acc,none,0.5877192982456141,0.046306532033665936,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7310344827586207,0.03695183311650232,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6402116402116402,0.024718075944129204,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_formal_logic,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.04216370213557839,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8516129032258064,0.02022273755433042,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6748768472906403,0.03295797566311267,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8686868686868687,0.02406315641682249,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8911917098445595,0.02247325333276875,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7435897435897436,0.022139081103971635,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4925925925925926,0.03048219239519157,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7899159663865546,0.026461398717471864,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_physics,5,lm-eval,vllm,,acc,none,0.6291390728476821,0.039439666991836285,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8844036697247707,0.01370874953417266,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.031919234456861886,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8284313725490197,0.026460569561240675,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7709923664122137,0.036853466317118506,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_humanities,5,lm-eval,vllm,yes,acc,none,0.6342189160467587,0.006700606386392462,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_jurisprudence,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.03602814176392641,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7791411042944786,0.032591773927421734,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_machine_learning,5,lm-eval,vllm,,acc,none,0.6071428571428571,0.04635550135609972,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_management,5,lm-eval,vllm,,acc,none,0.8446601941747572,0.03586594738573976,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_miscellaneous,5,lm-eval,vllm,,acc,none,0.789272030651341,0.01458381246586261,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7572254335260116,0.02308365858698422,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4748603351955307,0.01670135084268273,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_nutrition,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.02428861946604616,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_other,5,lm-eval,vllm,yes,acc,none,0.718056002574831,0.007845489488961003,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_philosophy,5,lm-eval,vllm,,acc,none,0.7331189710610932,0.0251226376088166,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_prehistory,5,lm-eval,vllm,,acc,none,0.7716049382716049,0.02335821184062624,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_professional_accounting,5,lm-eval,vllm,,acc,none,0.5177304964539007,0.02980873964223769,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_professional_law,5,lm-eval,vllm,,acc,none,0.5091264667535854,0.01276810860163994,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_professional_medicine,5,lm-eval,vllm,,acc,none,0.7132352941176471,0.027472274473233842,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_professional_psychology,5,lm-eval,vllm,,acc,none,0.7401960784313726,0.017740899509177833,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.793955151121222,0.0071742795828583315,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_stem,5,lm-eval,vllm,yes,acc,none,0.6701554075483667,0.008100836396297832,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_virology,5,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_pt_world_religions,5,lm-eval,vllm,,acc,none,0.8128654970760234,0.029913127232368063,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c402d3ec55_2026-10-07T15-47-43.085123.json,1791387722.4601912,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro,5,lm-eval,vllm,yes,acc,none,0.6960546930636662,0.0037215552626436465,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_abstract_algebra,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_anatomy,5,lm-eval,vllm,,acc,none,0.6,0.0423207369515159,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_business_ethics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7132075471698113,0.027834912527544126,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_college_computer_science,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_college_medicine,5,lm-eval,vllm,,acc,none,0.7283236994219653,0.03391750322321658,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_college_physics,5,lm-eval,vllm,,acc,none,0.5294117647058824,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7276595744680852,0.029101290698386736,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6896551724137931,0.03855289616378948,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6772486772486772,0.02407894324359702,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_biology,5,lm-eval,vllm,,acc,none,0.8548387096774194,0.020039563628053293,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.030117688929503603,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_geography,5,lm-eval,vllm,,acc,none,0.8686868686868687,0.02406315641682249,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7717948717948718,0.02127839386358626,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5074074074074074,0.03048219239519157,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8361344537815126,0.024044054940440488,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_physics,5,lm-eval,vllm,,acc,none,0.5894039735099338,0.04016689594849927,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8568807339449541,0.015014462497168531,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.030851992993257013,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.024857478080250486,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8185654008438819,0.025085961144579647,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_human_aging,5,lm-eval,vllm,,acc,none,0.7399103139013453,0.029442495585857424,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_humanities,5,lm-eval,vllm,yes,acc,none,0.6346439957492029,0.006705276680316758,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_international_law,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.03520893951097652,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_jurisprudence,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.03957835471980979,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_machine_learning,5,lm-eval,vllm,,acc,none,0.6071428571428571,0.04635550135609972,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_management,5,lm-eval,vllm,,acc,none,0.7766990291262136,0.041235531898914324,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_marketing,5,lm-eval,vllm,,acc,none,0.8760683760683761,0.021586494001281407,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_miscellaneous,5,lm-eval,vllm,,acc,none,0.789272030651341,0.01458381246586261,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_moral_disputes,5,lm-eval,vllm,,acc,none,0.7485549132947977,0.023357365785874006,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_moral_scenarios,5,lm-eval,vllm,,acc,none,0.46033519553072627,0.016669799592112056,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_nutrition,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.025261691219729484,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_other,5,lm-eval,vllm,yes,acc,none,0.7158030254264564,0.007851832073657736,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_prehistory,5,lm-eval,vllm,,acc,none,0.7808641975308642,0.02301670564026216,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_professional_accounting,5,lm-eval,vllm,,acc,none,0.5212765957446809,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_professional_law,5,lm-eval,vllm,,acc,none,0.5267275097783573,0.012751977967675987,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_professional_medicine,5,lm-eval,vllm,,acc,none,0.7389705882352942,0.026679252270103055,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_professional_psychology,5,lm-eval,vllm,,acc,none,0.7271241830065359,0.01802047414839352,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_public_relations,5,lm-eval,vllm,,acc,none,0.7181818181818181,0.043091187099464606,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_security_studies,5,lm-eval,vllm,,acc,none,0.7959183673469388,0.02580128347509046,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7998050048748782,0.00708128834715497,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_sociology,5,lm-eval,vllm,,acc,none,0.9154228855721394,0.01967534321719919,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_stem,5,lm-eval,vllm,yes,acc,none,0.6669838249286394,0.008183140976248069,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_virology,5,lm-eval,vllm,,acc,none,0.46987951807228917,0.038854254208667706,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_ro_world_religions,5,lm-eval,vllm,,acc,none,0.8421052631578947,0.027966785859160903,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6306610890_2026-10-07T15-53-52.991833.json,1791388090.7272153,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr,5,lm-eval,vllm,yes,acc,none,0.672696197122917,0.0038068761088118483,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_anatomy,5,lm-eval,vllm,,acc,none,0.5777777777777777,0.042667634040995855,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7245283018867924,0.027495663683724022,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_college_biology,5,lm-eval,vllm,,acc,none,0.7569444444444444,0.03586879280080337,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_college_chemistry,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_college_mathematics,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_college_physics,5,lm-eval,vllm,,acc,none,0.5784313725490197,0.049135952012745024,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_computer_security,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7319148936170212,0.028957342788342354,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6896551724137931,0.03855289616378948,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6904761904761905,0.02380952380952381,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_global_facts,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8354838709677419,0.021090847745939306,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6305418719211823,0.03395970381998578,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7696969696969697,0.03287666758603482,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026552207828215258,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8756476683937824,0.02381447708659357,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7538461538461538,0.02184086699042312,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48148148148148145,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5695364238410596,0.04042809961395634,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8587155963302753,0.014933868987028072,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6898148148148148,0.03154696285656624,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8088235294117647,0.02759917430064072,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8438818565400844,0.02362715946031866,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_human_aging,5,lm-eval,vllm,,acc,none,0.6995515695067265,0.030769352008229164,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7709923664122137,0.036853466317118506,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_humanities,5,lm-eval,vllm,yes,acc,none,0.6157279489904357,0.006799501585132925,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.04019107472557348,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7177914110429447,0.03536117886664741,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_management,5,lm-eval,vllm,,acc,none,0.7766990291262136,0.041235531898914324,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_marketing,5,lm-eval,vllm,,acc,none,0.8760683760683761,0.021586494001281407,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_medical_genetics,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7126436781609196,0.016182410730682734,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7196531791907514,0.024182427496577626,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.48156424581005586,0.016711130497782726,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_nutrition,5,lm-eval,vllm,,acc,none,0.7189542483660131,0.025738854797818695,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_other,5,lm-eval,vllm,yes,acc,none,0.6746057289990345,0.008183324711196639,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_philosophy,5,lm-eval,vllm,,acc,none,0.6977491961414791,0.026082700695399676,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_prehistory,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.024659685185967343,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_professional_accounting,5,lm-eval,vllm,,acc,none,0.46808510638297873,0.02976667507587383,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_professional_law,5,lm-eval,vllm,,acc,none,0.4921773142112125,0.012768673076111898,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6580882352941176,0.02881472242225415,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.01863559403442406,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7793305167370815,0.007357843995814308,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_sociology,5,lm-eval,vllm,,acc,none,0.8507462686567164,0.02519692987482706,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_stem,5,lm-eval,vllm,yes,acc,none,0.6517602283539486,0.008240381988709137,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sr_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c594219d82_2026-10-07T16-00-08.296588.json,1791388459.135,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv,5,lm-eval,vllm,yes,acc,none,0.690571143711722,0.0037240563529520754,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_anatomy,5,lm-eval,vllm,,acc,none,0.6,0.0423207369515159,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_astronomy,5,lm-eval,vllm,,acc,none,0.8289473684210527,0.03064360707167711,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_business_ethics,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7358490566037735,0.02713429162874164,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_college_biology,5,lm-eval,vllm,,acc,none,0.8125,0.032639560491693344,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_college_chemistry,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_college_medicine,5,lm-eval,vllm,,acc,none,0.6936416184971098,0.035149425512674394,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7489361702127659,0.02834696377716252,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7241379310344828,0.037245636197746325,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6904761904761905,0.02380952380952381,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_formal_logic,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.043435254289490965,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_biology,5,lm-eval,vllm,,acc,none,0.8483870967741935,0.020402616654416734,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6650246305418719,0.03320852742348313,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8363636363636363,0.028887872395487978,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7717948717948718,0.02127839386358626,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5074074074074074,0.03048219239519157,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8109243697478992,0.025435119438105305,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_physics,5,lm-eval,vllm,,acc,none,0.5695364238410596,0.04042809961395634,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8825688073394495,0.013802780227377303,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6990740740740741,0.03128039084329886,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.02675640153807894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8396624472573839,0.02388438092596563,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_human_aging,5,lm-eval,vllm,,acc,none,0.726457399103139,0.029918586707798872,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_humanities,5,lm-eval,vllm,yes,acc,none,0.6272051009564293,0.006706575187820901,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_international_law,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.03520893951097652,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_jurisprudence,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.03957835471980979,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6932515337423313,0.036230899157241474,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_machine_learning,5,lm-eval,vllm,,acc,none,0.6160714285714286,0.04616143075028549,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_management,5,lm-eval,vllm,,acc,none,0.7961165048543689,0.0398913985953177,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_marketing,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.02058849131609242,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_medical_genetics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_miscellaneous,5,lm-eval,vllm,,acc,none,0.7803320561941252,0.014805384478371247,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_moral_disputes,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.02378620325550823,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4592178770949721,0.016666783616525672,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_nutrition,5,lm-eval,vllm,,acc,none,0.7516339869281046,0.02473998135511354,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_other,5,lm-eval,vllm,yes,acc,none,0.7022851625362085,0.007875239973322517,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_philosophy,5,lm-eval,vllm,,acc,none,0.7556270096463023,0.024406162094668955,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_prehistory,5,lm-eval,vllm,,acc,none,0.7839506172839507,0.02289916291844576,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_professional_accounting,5,lm-eval,vllm,,acc,none,0.44680851063829785,0.02965823509766695,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_professional_law,5,lm-eval,vllm,,acc,none,0.5039113428943938,0.012769845366441192,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_professional_medicine,5,lm-eval,vllm,,acc,none,0.7132352941176471,0.027472274473233842,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_professional_psychology,5,lm-eval,vllm,,acc,none,0.7271241830065359,0.01802047414839352,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_security_studies,5,lm-eval,vllm,,acc,none,0.7714285714285715,0.026882144922307713,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7946051348716282,0.007161136815364482,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_sociology,5,lm-eval,vllm,,acc,none,0.845771144278607,0.025538433368578303,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_stem,5,lm-eval,vllm,yes,acc,none,0.672058357120203,0.008114890346986346,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_virology,5,lm-eval,vllm,,acc,none,0.45180722891566266,0.0387437155658795,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_sv_world_religions,5,lm-eval,vllm,,acc,none,0.8421052631578947,0.027966785859160903,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/40463757ee_2026-10-07T16-20-22.187246.json,1791389690.6153693,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr,5,lm-eval,vllm,yes,acc,none,0.6524711579547073,0.003859210857195098,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_business_ethics,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_college_biology,5,lm-eval,vllm,,acc,none,0.7361111111111112,0.036856510958975304,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_college_mathematics,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_college_medicine,5,lm-eval,vllm,,acc,none,0.6416184971098265,0.0365634365335316,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_computer_security,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6510638297872341,0.031158522131357808,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_econometrics,5,lm-eval,vllm,,acc,none,0.5350877192982456,0.04692008381368906,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6689655172413793,0.03921545312467122,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6455026455026455,0.024636830602842035,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_biology,5,lm-eval,vllm,,acc,none,0.7935483870967742,0.023025899617188667,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6403940886699507,0.0337645824650957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.793939393939394,0.03158415324047706,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8131313131313131,0.02777253333421894,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.772020725388601,0.030276909945178256,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7153846153846154,0.022878322799706304,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4703703703703704,0.030431963547936577,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7773109243697479,0.027025433498882392,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5165562913907285,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8422018348623853,0.015630022970092496,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6574074074074074,0.0323658525260216,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8016877637130801,0.02595502084162111,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_human_aging,5,lm-eval,vllm,,acc,none,0.7130044843049327,0.030360379710291947,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7404580152671756,0.03844876139785267,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_humanities,5,lm-eval,vllm,yes,acc,none,0.5946865037194474,0.00681466011576725,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_jurisprudence,5,lm-eval,vllm,,acc,none,0.8055555555555556,0.038260763248848646,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.656441717791411,0.037311335196738946,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_management,5,lm-eval,vllm,,acc,none,0.7766990291262136,0.041235531898914324,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_marketing,5,lm-eval,vllm,,acc,none,0.8376068376068376,0.024161618127987734,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_medical_genetics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7292464878671775,0.01588988836256046,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_moral_disputes,5,lm-eval,vllm,,acc,none,0.6820809248554913,0.025070713719153193,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4033519553072626,0.016407123032195232,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_nutrition,5,lm-eval,vllm,,acc,none,0.696078431372549,0.026336613469046647,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_other,5,lm-eval,vllm,yes,acc,none,0.6688123591889282,0.008214937266010615,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_philosophy,5,lm-eval,vllm,,acc,none,0.7041800643086816,0.025922371788818833,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_prehistory,5,lm-eval,vllm,,acc,none,0.7376543209876543,0.024477222856135194,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_professional_accounting,5,lm-eval,vllm,,acc,none,0.45390070921985815,0.029700453247291494,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_professional_law,5,lm-eval,vllm,,acc,none,0.4869621903520209,0.01276589388383549,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6875,0.02815637344037142,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6797385620915033,0.018875682938069425,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_security_studies,5,lm-eval,vllm,,acc,none,0.726530612244898,0.028535560337128486,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7497562560935976,0.007707918444205951,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_sociology,5,lm-eval,vllm,,acc,none,0.8109452736318408,0.02768691358801299,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_stem,5,lm-eval,vllm,yes,acc,none,0.6276562004440216,0.00835930896986842,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_virology,5,lm-eval,vllm,,acc,none,0.4819277108433735,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_tr_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35220401c8_2026-10-07T15-39-32.586361.json,1791387226.7798097,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk,5,lm-eval,vllm,yes,acc,none,0.6647913402649195,0.003801590290604188,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_abstract_algebra,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.690566037735849,0.028450154794118682,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_college_biology,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03476590104304133,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_college_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_college_mathematics,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_college_physics,5,lm-eval,vllm,,acc,none,0.6078431372549019,0.04858083574266346,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7489361702127659,0.02834696377716252,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_econometrics,5,lm-eval,vllm,,acc,none,0.5263157894736842,0.04697085136647865,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6620689655172414,0.03941707632064884,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6587301587301587,0.024419234966819043,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_formal_logic,5,lm-eval,vllm,,acc,none,0.5793650793650794,0.044154382267437474,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_global_facts,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_biology,5,lm-eval,vllm,,acc,none,0.8290322580645161,0.021417242936321575,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6650246305418719,0.03320852742348313,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8242424242424242,0.029720943006224455,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_geography,5,lm-eval,vllm,,acc,none,0.8383838383838383,0.02622591986362927,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7205128205128205,0.02275238883977686,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5111111111111111,0.0304780098196158,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7983193277310925,0.026064313406304485,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8697247706422019,0.01443186285247314,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.03167468706828983,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8227848101265823,0.024856364184503203,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_human_aging,5,lm-eval,vllm,,acc,none,0.6860986547085202,0.031146796482972486,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_humanities,5,lm-eval,vllm,yes,acc,none,0.585759829968119,0.0067911740887275735,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_jurisprudence,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.040774947092526284,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7300613496932515,0.034878251684978955,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_machine_learning,5,lm-eval,vllm,,acc,none,0.6071428571428571,0.04635550135609972,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_medical_genetics,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_miscellaneous,5,lm-eval,vllm,,acc,none,0.7318007662835249,0.01584243083526941,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_moral_disputes,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.024257901705323326,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3743016759776536,0.016185444179457154,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_nutrition,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.024630048979824716,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_other,5,lm-eval,vllm,yes,acc,none,0.6758931445123914,0.008185179274875252,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_philosophy,5,lm-eval,vllm,,acc,none,0.684887459807074,0.026385273703464482,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_prehistory,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.025630824975621306,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_professional_accounting,5,lm-eval,vllm,,acc,none,0.44680851063829785,0.02965823509766695,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_professional_law,5,lm-eval,vllm,,acc,none,0.47783572359843546,0.01275768304771619,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_professional_medicine,5,lm-eval,vllm,,acc,none,0.6433823529411765,0.029097209568412025,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_professional_psychology,5,lm-eval,vllm,,acc,none,0.7140522875816994,0.01828048507295479,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_security_studies,5,lm-eval,vllm,,acc,none,0.7714285714285715,0.026882144922307713,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7796555086122847,0.007324938587706294,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_stem,5,lm-eval,vllm,yes,acc,none,0.6596891849032668,0.008233412505258967,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_virology,5,lm-eval,vllm,,acc,none,0.5240963855421686,0.03887971849597267,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_mmlu_full_uk_world_religions,5,lm-eval,vllm,,acc,none,0.7485380116959064,0.03327504423846844,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09308ce348_2026-10-07T16-14-41.470279.json,1791389325.0096529,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/46e19f5865_2026-10-07T16-11-23.464590.json,1791389316.626115,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_bytes,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/46e19f5865_2026-10-07T16-11-23.464590.json,1791389316.626115,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_norm,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/46e19f5865_2026-10-07T16-11-23.464590.json,1791389316.626115,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9a0b16b411_2026-10-07T16-11-32.994061.json,1791389328.9434402,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_bytes,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9a0b16b411_2026-10-07T16-11-32.994061.json,1791389328.9434402,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_norm,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9a0b16b411_2026-10-07T16-11-32.994061.json,1791389328.9434402,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/77d655ec87_2026-10-07T15-47-26.385421.json,1791387864.923108,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/77d655ec87_2026-10-07T15-47-26.385421.json,1791387864.923108,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/77d655ec87_2026-10-07T15-47-26.385421.json,1791387864.923108,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c0ab4e7bc1_2026-10-07T16-11-32.803571.json,1791389310.7565107,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c0ab4e7bc1_2026-10-07T16-11-32.803571.json,1791389310.7565107,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c0ab4e7bc1_2026-10-07T16-11-32.803571.json,1791389310.7565107,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bd114f8d09_2026-10-07T16-11-23.757822.json,1791389324.8118577,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bd114f8d09_2026-10-07T16-11-23.757822.json,1791389324.8118577,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_norm,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bd114f8d09_2026-10-07T16-11-23.757822.json,1791389324.8118577,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/95db32636e_2026-10-07T15-47-00.965011.json,1791387863.177505,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/95db32636e_2026-10-07T15-47-00.965011.json,1791387863.177505,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/95db32636e_2026-10-07T15-47-00.965011.json,1791387863.177505,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/311d6c6cde_2026-10-07T16-11-15.169280.json,1791389314.093215,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/311d6c6cde_2026-10-07T16-11-15.169280.json,1791389314.093215,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/311d6c6cde_2026-10-07T16-11-15.169280.json,1791389314.093215,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b9aa15217_2026-10-07T15-47-08.657446.json,1791387867.0190456,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_bytes,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b9aa15217_2026-10-07T15-47-08.657446.json,1791387867.0190456,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_norm,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b9aa15217_2026-10-07T15-47-08.657446.json,1791387867.0190456,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e36442cb47_2026-10-07T15-44-41.421916.json,1791387719.8021874,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e36442cb47_2026-10-07T15-44-41.421916.json,1791387719.8021874,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e36442cb47_2026-10-07T15-44-41.421916.json,1791387719.8021874,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fac08bdbf_2026-10-07T15-36-28.962739.json,1791387225.219924,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fac08bdbf_2026-10-07T15-36-28.962739.json,1791387225.219924,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9fac08bdbf_2026-10-07T15-36-28.962739.json,1791387225.219924,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4544b68c14_2026-10-07T16-17-28.139667.json,1791389680.2363002,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_bytes,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4544b68c14_2026-10-07T16-17-28.139667.json,1791389680.2363002,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_norm,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4544b68c14_2026-10-07T16-17-28.139667.json,1791389680.2363002,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ea8aa9e3a_2026-10-07T15-53-00.629322.json,1791388218.6789796,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_bytes,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ea8aa9e3a_2026-10-07T15-53-00.629322.json,1791388218.6789796,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_norm,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ea8aa9e3a_2026-10-07T15-53-00.629322.json,1791388218.6789796,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6b6748ef8b_2026-10-07T16-11-30.494539.json,1791389327.8598042,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6b6748ef8b_2026-10-07T16-11-30.494539.json,1791389327.8598042,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6b6748ef8b_2026-10-07T16-11-30.494539.json,1791389327.8598042,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9387c6268_2026-10-07T16-17-36.756092.json,1791389689.4385736,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9387c6268_2026-10-07T16-17-36.756092.json,1791389689.4385736,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_norm,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9387c6268_2026-10-07T16-17-36.756092.json,1791389689.4385736,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0db752f770_2026-10-07T15-42-38.926326.json,1791387588.2309668,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_bytes,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0db752f770_2026-10-07T15-42-38.926326.json,1791387588.2309668,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_norm,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0db752f770_2026-10-07T15-42-38.926326.json,1791387588.2309668,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecfa8c27f8_2026-10-07T15-44-45.315574.json,1791387724.716334,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecfa8c27f8_2026-10-07T15-44-45.315574.json,1791387724.716334,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecfa8c27f8_2026-10-07T15-44-45.315574.json,1791387724.716334,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ae2a5aac17_2026-10-07T16-11-25.224835.json,1791389317.988702,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_bytes,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ae2a5aac17_2026-10-07T16-11-25.224835.json,1791389317.988702,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_norm,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ae2a5aac17_2026-10-07T16-11-25.224835.json,1791389317.988702,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f2bba214c3_2026-10-07T15-47-23.220379.json,1791387866.7962065,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f2bba214c3_2026-10-07T15-47-23.220379.json,1791387866.7962065,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f2bba214c3_2026-10-07T15-47-23.220379.json,1791387866.7962065,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc,none,0.91,0.028762349126466136,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3217384f31_2026-10-07T15-50-52.058355.json,1791388090.5680492,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3217384f31_2026-10-07T15-50-52.058355.json,1791388090.5680492,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3217384f31_2026-10-07T15-50-52.058355.json,1791388090.5680492,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d5ac6959b1_2026-10-07T15-46-59.425719.json,1791387854.0996244,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_bytes,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d5ac6959b1_2026-10-07T15-46-59.425719.json,1791387854.0996244,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d5ac6959b1_2026-10-07T15-46-59.425719.json,1791387854.0996244,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6d0bb9c92c_2026-10-07T15-52-47.265509.json,1791388210.0728483,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_bytes,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6d0bb9c92c_2026-10-07T15-52-47.265509.json,1791388210.0728483,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_norm,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6d0bb9c92c_2026-10-07T15-52-47.265509.json,1791388210.0728483,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d7f7dd5a4_2026-10-07T15-48-54.825075.json,1791387973.3284454,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d7f7dd5a4_2026-10-07T15-48-54.825075.json,1791387973.3284454,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d7f7dd5a4_2026-10-07T15-48-54.825075.json,1791387973.3284454,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5caa2eccf7_2026-10-07T15-42-46.556331.json,1791387604.1586056,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_bytes,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5caa2eccf7_2026-10-07T15-42-46.556331.json,1791387604.1586056,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5caa2eccf7_2026-10-07T15-42-46.556331.json,1791387604.1586056,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26e6abcbf2_2026-10-07T15-48-44.134517.json,1791387969.2972262,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26e6abcbf2_2026-10-07T15-48-44.134517.json,1791387969.2972262,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26e6abcbf2_2026-10-07T15-48-44.134517.json,1791387969.2972262,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/47e64c3ac0_2026-10-07T15-52-44.547929.json,1791388202.8854005,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/47e64c3ac0_2026-10-07T15-52-44.547929.json,1791388202.8854005,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/47e64c3ac0_2026-10-07T15-52-44.547929.json,1791388202.8854005,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d9dc28f238_2026-10-07T16-17-23.587417.json,1791389683.0005739,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d9dc28f238_2026-10-07T16-17-23.587417.json,1791389683.0005739,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d9dc28f238_2026-10-07T16-17-23.587417.json,1791389683.0005739,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d03c3d1b60_2026-10-07T15-48-49.321873.json,1791387967.4282174,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_bytes,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d03c3d1b60_2026-10-07T15-48-49.321873.json,1791387967.4282174,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_norm,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d03c3d1b60_2026-10-07T15-48-49.321873.json,1791387967.4282174,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35681ac4ef_2026-10-07T15-36-19.534110.json,1791387224.9254384,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35681ac4ef_2026-10-07T15-36-19.534110.json,1791387224.9254384,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/35681ac4ef_2026-10-07T15-36-19.534110.json,1791387224.9254384,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc,none,0.93,0.02564323999762428,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b7abd5e43_2026-10-07T15-50-51.453046.json,1791388086.4519827,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.91,0.028762349126466136,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b7abd5e43_2026-10-07T15-50-51.453046.json,1791388086.4519827,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_norm,none,0.91,0.028762349126466136,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b7abd5e43_2026-10-07T15-50-51.453046.json,1791388086.4519827,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ed01ae3384_2026-10-07T15-44-43.201913.json,1791387721.6860747,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ed01ae3384_2026-10-07T15-44-43.201913.json,1791387721.6860747,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ed01ae3384_2026-10-07T15-44-43.201913.json,1791387721.6860747,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d16ff5edac_2026-10-07T15-44-48.744103.json,1791387724.5890841,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_bytes,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d16ff5edac_2026-10-07T15-44-48.744103.json,1791387724.5890841,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_norm,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d16ff5edac_2026-10-07T15-44-48.744103.json,1791387724.5890841,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ae6173dff9_2026-10-07T15-48-50.167148.json,1791387970.134491,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ae6173dff9_2026-10-07T15-48-50.167148.json,1791387970.134491,1 +v1annealTT_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ae6173dff9_2026-10-07T15-48-50.167148.json,1791387970.134491,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_als_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/adee6900ea_2026-10-07T15-48-59.237970.json,1791387971.9698744,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_bos_latn,0,lm-eval,vllm,,exact_match,strict_match,0.63,0.04852365870939099,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/62d780cb19_2026-10-07T15-45-09.901673.json,1791387728.4104311,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_bul_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.56,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9208b600ed_2026-10-07T15-44-44.671714.json,1791387721.4522467,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_cat_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4caa4400fe_2026-10-07T16-11-44.637052.json,1791389323.0498996,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_ces_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3689ee3d33_2026-10-07T15-44-49.561862.json,1791387723.2174037,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_deu_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3da5c82f1a_2026-10-07T15-44-57.354132.json,1791387728.2625563,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_ekk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/31fda90089_2026-10-07T15-44-52.743877.json,1791387726.453444,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_ell_grek,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/16a4ec3d11_2026-10-07T15-52-54.564954.json,1791388208.0760858,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_eng_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ccb69958f9_2026-10-07T15-48-51.596080.json,1791387961.0580904,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_fin_latn,0,lm-eval,vllm,,exact_match,strict_match,0.58,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/07ff721d0e_2026-10-07T15-52-53.863092.json,1791388205.4201815,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_fra_latn_fran,0,lm-eval,vllm,,exact_match,strict_match,0.51,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/68a4de8897_2026-10-07T16-11-34.856623.json,1791389324.7603238,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_glg_latn,0,lm-eval,vllm,,exact_match,strict_match,0.51,0.05024183937956911,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/20ebdcc340_2026-10-07T15-44-50.791928.json,1791387724.6410916,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_hrv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/810b7e7b9b_2026-10-07T16-17-28.848732.json,1791389684.3321161,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_hun_latn,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d179be9dc5_2026-10-07T16-11-30.794528.json,1791389322.8764462,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_isl_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.049020713000019756,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/79360440a8_2026-10-07T16-17-35.301798.json,1791389673.1462045,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_ita_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.049999999999999996,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/48dfe49326_2026-10-07T15-44-39.131402.json,1791387716.1142766,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_kat_geor,0,lm-eval,vllm,,exact_match,strict_match,0.27,0.0446196043338474,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c4aee7664b_2026-10-07T16-11-36.581453.json,1791389326.999068,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_lit_latn,0,lm-eval,vllm,,exact_match,strict_match,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e11f2efd9f_2026-10-07T15-49-01.280191.json,1791387970.8223383,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_mkd_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2e8160c12e_2026-10-07T16-21-29.182322.json,1791389926.0227308,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_nld_latn,0,lm-eval,vllm,,exact_match,strict_match,0.35,0.0479372485441102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/198189cfe6_2026-10-07T15-50-54.840859.json,1791388088.6720371,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_nno_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6be8f4dcdc_2026-10-07T15-50-51.628658.json,1791388087.507731,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_nob_latn,0,lm-eval,vllm,,exact_match,strict_match,0.48,0.050211673156867795,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/722a6c0a4b_2026-10-07T15-44-51.101882.json,1791387722.1791477,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_pol_latn,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.049756985195624284,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/730b12515f_2026-10-07T15-47-00.544106.json,1791387855.542751,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_por_latn_port,0,lm-eval,vllm,,exact_match,strict_match,0.55,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/267826768b_2026-10-07T16-11-34.136123.json,1791389317.0914755,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_ron_latn,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.04975698519562428,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/686b3c1d4a_2026-10-07T15-52-55.120185.json,1791388207.6798227,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_slk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.55,0.04999999999999999,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e93b23fcb8_2026-10-07T15-44-43.987411.json,1791387716.9300451,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_slv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c065563587_2026-10-07T15-45-02.876908.json,1791387721.3165665,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_spa_latn_spai,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7bad0ab418_2026-10-07T15-53-03.332844.json,1791388218.6354165,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_srp_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.48,0.050211673156867795,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4692abbc3a_2026-10-07T15-48-56.600344.json,1791387968.416841,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_swe_latn,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f4c6641ebe_2026-10-07T15-50-51.400715.json,1791388083.8197796,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_tur_latn,0,lm-eval,vllm,,exact_match,strict_match,0.54,0.05009082659620333,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5320773d79_2026-10-07T15-44-53.127613.json,1791387726.4923718,1 +v1annealTT_merge3_116k_120k,global_piqa_prompted_ukr_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.54,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/777d295fac_2026-10-07T15-44-40.203135.json,1791387720.6059988,1 +v1annealTT_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,flexible-extract,0.8369977255496588,0.010174223319872463,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1822554c01_2026-10-07T16-12-28.312681.json,1791389325.1540468,1 +v1annealTT_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,strict-match,0.8339651250947687,0.010249811990593528,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1822554c01_2026-10-07T16-12-28.312681.json,1791389325.1540468,1 +v1annealTT_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc,none,0.6133240390360486,0.0048599309265002074,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1692f554c0_2026-10-07T15-46-17.228280.json,1791387727.330776,1 +v1annealTT_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc_norm,none,0.8053176658036247,0.0039514673865973515,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1692f554c0_2026-10-07T15-46-17.228280.json,1791387727.330776,1 +v1annealTT_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc,none,0.6331408086038638,0.004809626723626934,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4e85737c3a_2026-10-07T15-49-11.886738.json,1791387591.5126736,1 +v1annealTT_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc_norm,none,0.8292172873929496,0.0037554989417820004,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4e85737c3a_2026-10-07T15-49-11.886738.json,1791387591.5126736,1 +v1annealTT_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc,none,0.5146021061773965,0.0052078073280029166,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/54d9fb18c3_2026-10-07T15-50-22.849167.json,1791387964.0500164,1 +v1annealTT_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc_norm,none,0.6747367278254262,0.004881517758815061,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/54d9fb18c3_2026-10-07T15-50-22.849167.json,1791387964.0500164,1 +v1annealTT_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc,none,0.5396023643202579,0.005167358743325994,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5ca4c60e9_2026-10-07T15-54-27.322598.json,1791388221.3650477,1 +v1annealTT_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc_norm,none,0.7034927458355723,0.00473491974625458,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f5ca4c60e9_2026-10-07T15-54-27.322598.json,1791388221.3650477,1 +v1annealTT_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc,none,0.5389624252775406,0.005150473359974041,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1e7d2e9471_2026-10-07T15-48-24.465883.json,1791387857.91329,1 +v1annealTT_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc_norm,none,0.6922502134927413,0.004769031260794468,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1e7d2e9471_2026-10-07T15-48-24.465883.json,1791387857.91329,1 +v1annealTT_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc,none,0.56710049071901,0.005117811075066299,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6fde6d8c03_2026-10-07T15-38-03.557380.json,1791387229.7748508,1 +v1annealTT_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc_norm,none,0.7429059099637295,0.004514125664364783,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6fde6d8c03_2026-10-07T15-38-03.557380.json,1791387229.7748508,1 +v1annealTT_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc,none,0.302215018908698,0.004773688571510841,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a2c0803b1c_2026-10-07T16-23-07.919791.json,1791389935.5112164,1 +v1annealTT_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc_norm,none,0.3628309022150189,0.004998212762627688,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a2c0803b1c_2026-10-07T16-23-07.919791.json,1791389935.5112164,1 +v1annealTT_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc,none,0.5553651745555793,0.005142654874563968,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc7e337859_2026-10-07T15-40-13.802257.json,1791387348.659028,1 +v1annealTT_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc_norm,none,0.7302420218462198,0.004593216116308657,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc7e337859_2026-10-07T15-40-13.802257.json,1791387348.659028,1 +v1annealTT_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc,none,0.4989969380213283,0.005138000484892209,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/caa1ce16ee_2026-10-07T15-46-25.220856.json,1791387733.7063856,1 +v1annealTT_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc_norm,none,0.6647661281807623,0.004851023722005429,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/caa1ce16ee_2026-10-07T15-46-25.220856.json,1791387733.7063856,1 +v1annealTT_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc,none,0.45191358701612017,0.005211976195630946,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e894b7cea2_2026-10-07T16-19-03.396169.json,1791389683.0555255,1 +v1annealTT_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc_norm,none,0.5931571444237307,0.00514456235976654,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e894b7cea2_2026-10-07T16-19-03.396169.json,1791389683.0555255,1 +v1annealTT_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc,none,0.54236919395192,0.0051963706978514525,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e752f2105b_2026-10-07T16-16-39.461726.json,1791389563.91803,1 +v1annealTT_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc_norm,none,0.7132600891983031,0.004716969051840802,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e752f2105b_2026-10-07T16-16-39.461726.json,1791389563.91803,1 +v1annealTT_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc,none,0.5396654074473827,0.005178450426355808,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9d40b4f2b1_2026-10-07T15-46-16.763668.json,1791387728.2759056,1 +v1annealTT_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc_norm,none,0.7030760928224501,0.004747057316419071,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9d40b4f2b1_2026-10-07T15-46-16.763668.json,1791387728.2759056,1 +v1annealTT_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc,none,0.5472965651749919,0.005181606909540997,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ad9235d8c3_2026-10-07T15-46-11.473747.json,1791387721.4999459,1 +v1annealTT_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc_norm,none,0.7256474157546863,0.0046447630246063,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ad9235d8c3_2026-10-07T15-46-11.473747.json,1791387721.4999459,1 +v1annealTT_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc,none,0.5208220659816117,0.005195928006235458,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/81624b5635_2026-10-07T15-46-35.671676.json,1791387728.3052464,1 +v1annealTT_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc_norm,none,0.6777717685235263,0.004860641191300669,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/81624b5635_2026-10-07T15-46-35.671676.json,1791387728.3052464,1 +v1annealTT_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc,none,0.4775962045334739,0.005129060508369214,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/42697501f0_2026-10-07T15-46-15.289966.json,1791387724.1550083,1 +v1annealTT_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc_norm,none,0.622140221402214,0.004978674114882325,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/42697501f0_2026-10-07T15-46-15.289966.json,1791387724.1550083,1 +v1annealTT_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc,none,0.5026986982749497,0.005143914437428688,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93c1bc8391_2026-10-07T15-54-36.417338.json,1791388222.6601508,1 +v1annealTT_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc_norm,none,0.6626097999788337,0.004864354493575314,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93c1bc8391_2026-10-07T15-54-36.417338.json,1791388222.6601508,1 +v1annealTT_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc,none,0.5396842797632099,0.005218870967980246,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/37e37badd3_2026-10-07T15-50-21.337685.json,1791387975.7768016,1 +v1annealTT_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc_norm,none,0.7069721552291164,0.0047657841885794935,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/37e37badd3_2026-10-07T15-50-21.337685.json,1791387975.7768016,1 +v1annealTT_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc,none,0.4708258050802423,0.0051461305962651515,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5f800f41e4_2026-10-07T16-23-13.429805.json,1791389933.6353161,1 +v1annealTT_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc_norm,none,0.6105856095227973,0.005027251659096165,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5f800f41e4_2026-10-07T16-23-13.429805.json,1791389933.6353161,1 +v1annealTT_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_loose_acc,none,0.41606714628297364,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/328281a90c_2026-10-07T16-13-08.780619.json,1791389324.190415,1 +v1annealTT_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_strict_acc,none,0.38369304556354916,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/328281a90c_2026-10-07T16-13-08.780619.json,1791389324.190415,1 +v1annealTT_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_loose_acc,none,0.28835489833641403,0.019493890350654804,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/328281a90c_2026-10-07T16-13-08.780619.json,1791389324.190415,1 +v1annealTT_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_strict_acc,none,0.26062846580406657,0.018890584986760186,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/328281a90c_2026-10-07T16-13-08.780619.json,1791389324.190415,1 +v1annealTT_merge3_116k_120k,include_base_44_albanian,0,lm-eval,vllm,yes,acc,none,0.7676950998185118,0.0179795097403974,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d3f460ccb_2026-10-07T15-50-55.587927.json,1791388092.922514,1 +v1annealTT_merge3_116k_120k,include_base_44_albanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.7713004484304933,0.028188240046929196,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d3f460ccb_2026-10-07T15-50-55.587927.json,1791388092.922514,1 +v1annealTT_merge3_116k_120k,include_base_44_albanian_business_commerce,0,lm-eval,vllm,,acc,none,0.7892376681614349,0.027373095500540158,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d3f460ccb_2026-10-07T15-50-55.587927.json,1791388092.922514,1 +v1annealTT_merge3_116k_120k,include_base_44_albanian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d3f460ccb_2026-10-07T15-50-55.587927.json,1791388092.922514,1 +v1annealTT_merge3_116k_120k,include_base_44_albanian_social_science,0,lm-eval,vllm,,acc,none,0.7818181818181819,0.05620374845754972,55,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d3f460ccb_2026-10-07T15-50-55.587927.json,1791388092.922514,1 +v1annealTT_merge3_116k_120k,include_base_44_albanian_stem,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d3f460ccb_2026-10-07T15-50-55.587927.json,1791388092.922514,1 +v1annealTT_merge3_116k_120k,include_base_44_basque,0,lm-eval,vllm,yes,acc,none,0.476,0.022357273881016475,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/88afb951ca_2026-10-07T15-53-07.331118.json,1791388221.7961133,1 +v1annealTT_merge3_116k_120k,include_base_44_basque_professional_certification,0,lm-eval,vllm,,acc,none,0.476,0.022357273881016475,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/88afb951ca_2026-10-07T15-53-07.331118.json,1791388221.7961133,1 +v1annealTT_merge3_116k_120k,include_base_44_bulgarian,0,lm-eval,vllm,yes,acc,none,0.7163636363636363,0.01905251090660848,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/acf9ab648a_2026-10-07T15-42-52.623329.json,1791387594.4208024,1 +v1annealTT_merge3_116k_120k,include_base_44_bulgarian_arts_humanities,0,lm-eval,vllm,,acc,none,0.788,0.025901884690541117,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/acf9ab648a_2026-10-07T15-42-52.623329.json,1791387594.4208024,1 +v1annealTT_merge3_116k_120k,include_base_44_bulgarian_social_science,0,lm-eval,vllm,,acc,none,0.668,0.029844039047465857,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/acf9ab648a_2026-10-07T15-42-52.623329.json,1791387594.4208024,1 +v1annealTT_merge3_116k_120k,include_base_44_bulgarian_stem,0,lm-eval,vllm,,acc,none,0.6,0.06998542122237651,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/acf9ab648a_2026-10-07T15-42-52.623329.json,1791387594.4208024,1 +v1annealTT_merge3_116k_120k,include_base_44_croatian,0,lm-eval,vllm,yes,acc,none,0.7490909090909091,0.01841230015709483,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ec688d2e2a_2026-10-07T15-36-54.143406.json,1791387227.4606853,1 +v1annealTT_merge3_116k_120k,include_base_44_croatian_arts_humanities,0,lm-eval,vllm,,acc,none,0.704,0.028928939388379697,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ec688d2e2a_2026-10-07T15-36-54.143406.json,1791387227.4606853,1 +v1annealTT_merge3_116k_120k,include_base_44_croatian_social_science,0,lm-eval,vllm,,acc,none,0.804,0.025156857313255922,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ec688d2e2a_2026-10-07T15-36-54.143406.json,1791387227.4606853,1 +v1annealTT_merge3_116k_120k,include_base_44_croatian_stem,0,lm-eval,vllm,,acc,none,0.7,0.06546536707079771,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ec688d2e2a_2026-10-07T15-36-54.143406.json,1791387227.4606853,1 +v1annealTT_merge3_116k_120k,include_base_44_dutch,0,lm-eval,vllm,yes,acc,none,0.720508166969147,0.019054122229113023,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f92fdadde2_2026-10-07T15-47-04.151257.json,1791387860.6521077,1 +v1annealTT_merge3_116k_120k,include_base_44_dutch_applied_science,0,lm-eval,vllm,,acc,none,0.9333333333333333,0.06666666666666665,15,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f92fdadde2_2026-10-07T15-47-04.151257.json,1791387860.6521077,1 +v1annealTT_merge3_116k_120k,include_base_44_dutch_arts_humanities,0,lm-eval,vllm,,acc,none,0.7407407407407407,0.028170371263773586,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f92fdadde2_2026-10-07T15-47-04.151257.json,1791387860.6521077,1 +v1annealTT_merge3_116k_120k,include_base_44_dutch_health_oriented_education,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f92fdadde2_2026-10-07T15-47-04.151257.json,1791387860.6521077,1 +v1annealTT_merge3_116k_120k,include_base_44_dutch_social_science,0,lm-eval,vllm,,acc,none,0.6954732510288066,0.029583207218060927,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f92fdadde2_2026-10-07T15-47-04.151257.json,1791387860.6521077,1 +v1annealTT_merge3_116k_120k,include_base_44_dutch_stem,0,lm-eval,vllm,,acc,none,0.8,0.08164965809277261,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f92fdadde2_2026-10-07T15-47-04.151257.json,1791387860.6521077,1 +v1annealTT_merge3_116k_120k,include_base_44_estonian,0,lm-eval,vllm,yes,acc,none,0.7053571428571429,0.030181152244339853,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e18ee8f3e3_2026-10-07T15-36-26.586951.json,1791387226.6780891,1 +v1annealTT_merge3_116k_120k,include_base_44_estonian_applied_science,0,lm-eval,vllm,,acc,none,0.9285714285714286,0.07142857142857144,14,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e18ee8f3e3_2026-10-07T15-36-26.586951.json,1791387226.6780891,1 +v1annealTT_merge3_116k_120k,include_base_44_estonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6583850931677019,0.03749284617282496,161,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e18ee8f3e3_2026-10-07T15-36-26.586951.json,1791387226.6780891,1 +v1annealTT_merge3_116k_120k,include_base_44_estonian_health_oriented_education,0,lm-eval,vllm,,acc,none,1.0,0.0,2,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e18ee8f3e3_2026-10-07T15-36-26.586951.json,1791387226.6780891,1 +v1annealTT_merge3_116k_120k,include_base_44_estonian_social_science,0,lm-eval,vllm,,acc,none,0.6363636363636364,0.15212000482437738,11,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e18ee8f3e3_2026-10-07T15-36-26.586951.json,1791387226.6780891,1 +v1annealTT_merge3_116k_120k,include_base_44_estonian_stem,0,lm-eval,vllm,,acc,none,0.8333333333333334,0.0629940788348712,36,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e18ee8f3e3_2026-10-07T15-36-26.586951.json,1791387226.6780891,1 +v1annealTT_merge3_116k_120k,include_base_44_finnish,0,lm-eval,vllm,yes,acc,none,0.52994555353902,0.02129073746015583,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05d0efd864_2026-10-07T16-11-29.869249.json,1791389325.1663215,1 +v1annealTT_merge3_116k_120k,include_base_44_finnish_applied_science,0,lm-eval,vllm,,acc,none,0.5517241379310345,0.09398415777506855,29,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05d0efd864_2026-10-07T16-11-29.869249.json,1791389325.1663215,1 +v1annealTT_merge3_116k_120k,include_base_44_finnish_arts_humanities,0,lm-eval,vllm,,acc,none,0.4823008849557522,0.03331244287560834,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05d0efd864_2026-10-07T16-11-29.869249.json,1791389325.1663215,1 +v1annealTT_merge3_116k_120k,include_base_44_finnish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5777777777777777,0.07446027270295803,45,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05d0efd864_2026-10-07T16-11-29.869249.json,1791389325.1663215,1 +v1annealTT_merge3_116k_120k,include_base_44_finnish_social_science,0,lm-eval,vllm,,acc,none,0.5619469026548672,0.033076516090319925,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05d0efd864_2026-10-07T16-11-29.869249.json,1791389325.1663215,1 +v1annealTT_merge3_116k_120k,include_base_44_finnish_stem,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05d0efd864_2026-10-07T16-11-29.869249.json,1791389325.1663215,1 +v1annealTT_merge3_116k_120k,include_base_44_french,0,lm-eval,vllm,yes,acc,none,0.6372315035799523,0.02325435216389627,419,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/505d2f3cdb_2026-10-07T15-47-01.540632.json,1791387863.2388408,1 +v1annealTT_merge3_116k_120k,include_base_44_french_arts_humanities,0,lm-eval,vllm,,acc,none,0.6917293233082706,0.028366859921843336,266,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/505d2f3cdb_2026-10-07T15-47-01.540632.json,1791387863.2388408,1 +v1annealTT_merge3_116k_120k,include_base_44_french_driving_license,0,lm-eval,vllm,,acc,none,0.48936170212765956,0.07370428968378202,47,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/505d2f3cdb_2026-10-07T15-47-01.540632.json,1791387863.2388408,1 +v1annealTT_merge3_116k_120k,include_base_44_french_health_oriented_education,0,lm-eval,vllm,,acc,none,0.625,0.125,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/505d2f3cdb_2026-10-07T15-47-01.540632.json,1791387863.2388408,1 +v1annealTT_merge3_116k_120k,include_base_44_french_social_science,0,lm-eval,vllm,,acc,none,0.5945945945945946,0.057463730392271574,74,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/505d2f3cdb_2026-10-07T15-47-01.540632.json,1791387863.2388408,1 +v1annealTT_merge3_116k_120k,include_base_44_french_stem,0,lm-eval,vllm,,acc,none,0.375,0.125,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/505d2f3cdb_2026-10-07T15-47-01.540632.json,1791387863.2388408,1 +v1annealTT_merge3_116k_120k,include_base_44_georgian,0,lm-eval,vllm,yes,acc,none,0.48,0.022365160424231326,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/63792835de_2026-10-07T15-45-00.497141.json,1791387722.199764,1 +v1annealTT_merge3_116k_120k,include_base_44_georgian_arts_humanities,0,lm-eval,vllm,,acc,none,0.48,0.022365160424231326,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/63792835de_2026-10-07T15-45-00.497141.json,1791387722.199764,1 +v1annealTT_merge3_116k_120k,include_base_44_german,0,lm-eval,vllm,yes,acc,none,0.5251798561151079,0.04252133867266714,139,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8db11d3d8_2026-10-07T16-11-23.726380.json,1791389323.050057,1 +v1annealTT_merge3_116k_120k,include_base_44_german_driving_license,0,lm-eval,vllm,,acc,none,0.5652173913043478,0.10568965974008647,23,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8db11d3d8_2026-10-07T16-11-23.726380.json,1791389323.050057,1 +v1annealTT_merge3_116k_120k,include_base_44_german_social_science,0,lm-eval,vllm,,acc,none,0.5494505494505495,0.052446231001012276,91,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8db11d3d8_2026-10-07T16-11-23.726380.json,1791389323.050057,1 +v1annealTT_merge3_116k_120k,include_base_44_german_stem,0,lm-eval,vllm,,acc,none,0.4,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8db11d3d8_2026-10-07T16-11-23.726380.json,1791389323.050057,1 +v1annealTT_merge3_116k_120k,include_base_44_greek,0,lm-eval,vllm,yes,acc,none,0.6159420289855072,0.0203423444833425,552,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8abb9f41a_2026-10-07T15-50-50.908041.json,1791388085.157158,1 +v1annealTT_merge3_116k_120k,include_base_44_greek_arts_humanities,0,lm-eval,vllm,,acc,none,0.4594594594594595,0.08305895907471071,37,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8abb9f41a_2026-10-07T15-50-50.908041.json,1791388085.157158,1 +v1annealTT_merge3_116k_120k,include_base_44_greek_business_commerce,0,lm-eval,vllm,,acc,none,0.7619047619047619,0.05409160326162522,63,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8abb9f41a_2026-10-07T15-50-50.908041.json,1791388085.157158,1 +v1annealTT_merge3_116k_120k,include_base_44_greek_health_oriented_education,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8abb9f41a_2026-10-07T15-50-50.908041.json,1791388085.157158,1 +v1annealTT_merge3_116k_120k,include_base_44_greek_medical_license,0,lm-eval,vllm,,acc,none,0.6791044776119403,0.04047849016651382,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8abb9f41a_2026-10-07T15-50-50.908041.json,1791388085.157158,1 +v1annealTT_merge3_116k_120k,include_base_44_greek_professional_certification,0,lm-eval,vllm,,acc,none,0.48507462686567165,0.04333617784312706,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8abb9f41a_2026-10-07T15-50-50.908041.json,1791388085.157158,1 +v1annealTT_merge3_116k_120k,include_base_44_greek_social_science,0,lm-eval,vllm,,acc,none,0.6791044776119403,0.04047849016651382,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8abb9f41a_2026-10-07T15-50-50.908041.json,1791388085.157158,1 +v1annealTT_merge3_116k_120k,include_base_44_greek_stem,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8abb9f41a_2026-10-07T15-50-50.908041.json,1791388085.157158,1 +v1annealTT_merge3_116k_120k,include_base_44_hungarian,0,lm-eval,vllm,yes,acc,none,0.5490909090909091,0.021272140936474775,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/490d2695ba_2026-10-07T15-50-46.651417.json,1791388087.5468066,1 +v1annealTT_merge3_116k_120k,include_base_44_hungarian_applied_science,0,lm-eval,vllm,,acc,none,0.5425219941348973,0.027018070206633264,341,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/490d2695ba_2026-10-07T15-50-46.651417.json,1791388087.5468066,1 +v1annealTT_merge3_116k_120k,include_base_44_hungarian_social_science,0,lm-eval,vllm,,acc,none,0.5597826086956522,0.03669591776834159,184,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/490d2695ba_2026-10-07T15-50-46.651417.json,1791388087.5468066,1 +v1annealTT_merge3_116k_120k,include_base_44_hungarian_stem,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/490d2695ba_2026-10-07T15-50-46.651417.json,1791388087.5468066,1 +v1annealTT_merge3_116k_120k,include_base_44_italian,0,lm-eval,vllm,yes,acc,none,0.7098540145985401,0.019206175848436133,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9cc1aceea8_2026-10-07T16-11-25.432662.json,1791389323.0927804,1 +v1annealTT_merge3_116k_120k,include_base_44_italian_applied_science,0,lm-eval,vllm,,acc,none,0.6857142857142857,0.07961491954505553,35,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9cc1aceea8_2026-10-07T16-11-25.432662.json,1791389323.0927804,1 +v1annealTT_merge3_116k_120k,include_base_44_italian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6107784431137725,0.03784306023672045,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9cc1aceea8_2026-10-07T16-11-25.432662.json,1791389323.0927804,1 +v1annealTT_merge3_116k_120k,include_base_44_italian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.9166666666666666,0.08333333333333333,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9cc1aceea8_2026-10-07T16-11-25.432662.json,1791389323.0927804,1 +v1annealTT_merge3_116k_120k,include_base_44_italian_professional_certification,0,lm-eval,vllm,,acc,none,0.7225806451612903,0.036078724924879055,155,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9cc1aceea8_2026-10-07T16-11-25.432662.json,1791389323.0927804,1 +v1annealTT_merge3_116k_120k,include_base_44_italian_social_science,0,lm-eval,vllm,,acc,none,0.7904191616766467,0.0315900615882718,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9cc1aceea8_2026-10-07T16-11-25.432662.json,1791389323.0927804,1 +v1annealTT_merge3_116k_120k,include_base_44_italian_stem,0,lm-eval,vllm,,acc,none,0.6666666666666666,0.1421338109037403,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9cc1aceea8_2026-10-07T16-11-25.432662.json,1791389323.0927804,1 +v1annealTT_merge3_116k_120k,include_base_44_lithuanian,0,lm-eval,vllm,yes,acc,none,0.651685393258427,0.02056742550522242,534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d164a3a0fd_2026-10-07T15-42-35.549091.json,1791387593.9636402,1 +v1annealTT_merge3_116k_120k,include_base_44_lithuanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6746268656716418,0.025635950721950195,335,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d164a3a0fd_2026-10-07T15-42-35.549091.json,1791387593.9636402,1 +v1annealTT_merge3_116k_120k,include_base_44_lithuanian_business_commerce,0,lm-eval,vllm,,acc,none,0.5,0.08006407690254357,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d164a3a0fd_2026-10-07T15-42-35.549091.json,1791387593.9636402,1 +v1annealTT_merge3_116k_120k,include_base_44_lithuanian_professional_certification,0,lm-eval,vllm,,acc,none,0.5625,0.07236046734262122,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d164a3a0fd_2026-10-07T15-42-35.549091.json,1791387593.9636402,1 +v1annealTT_merge3_116k_120k,include_base_44_lithuanian_social_science,0,lm-eval,vllm,,acc,none,0.6493506493506493,0.05473553444308601,77,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d164a3a0fd_2026-10-07T15-42-35.549091.json,1791387593.9636402,1 +v1annealTT_merge3_116k_120k,include_base_44_lithuanian_stem,0,lm-eval,vllm,,acc,none,0.7352941176470589,0.07679896586280788,34,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d164a3a0fd_2026-10-07T15-42-35.549091.json,1791387593.9636402,1 +v1annealTT_merge3_116k_120k,include_base_44_north macedonian,0,lm-eval,vllm,yes,acc,none,0.8003629764065335,0.016935136255095563,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc07a2bfe9_2026-10-07T15-48-54.273830.json,1791387970.0132928,1 +v1annealTT_merge3_116k_120k,include_base_44_north macedonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.8482142857142857,0.02402789963038668,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc07a2bfe9_2026-10-07T15-48-54.273830.json,1791387970.0132928,1 +v1annealTT_merge3_116k_120k,include_base_44_north macedonian_business_commerce,0,lm-eval,vllm,,acc,none,0.7678571428571429,0.028272580246830843,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc07a2bfe9_2026-10-07T15-48-54.273830.json,1791387970.0132928,1 +v1annealTT_merge3_116k_120k,include_base_44_north macedonian_social_science,0,lm-eval,vllm,,acc,none,0.8490566037735849,0.0496447935456809,53,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc07a2bfe9_2026-10-07T15-48-54.273830.json,1791387970.0132928,1 +v1annealTT_merge3_116k_120k,include_base_44_north macedonian_stem,0,lm-eval,vllm,,acc,none,0.68,0.06663945022680344,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc07a2bfe9_2026-10-07T15-48-54.273830.json,1791387970.0132928,1 +v1annealTT_merge3_116k_120k,include_base_44_polish,0,lm-eval,vllm,yes,acc,none,0.5638686131386861,0.020829251081033024,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/63ed3cabf3_2026-10-07T15-53-08.736481.json,1791388226.89617,1 +v1annealTT_merge3_116k_120k,include_base_44_polish_professional_certification,0,lm-eval,vllm,,acc,none,0.5887096774193549,0.022116797087243237,496,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/63ed3cabf3_2026-10-07T15-53-08.736481.json,1791388226.89617,1 +v1annealTT_merge3_116k_120k,include_base_44_polish_social_science,0,lm-eval,vllm,,acc,none,1.0,0.0,4,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/63ed3cabf3_2026-10-07T15-53-08.736481.json,1791388226.89617,1 +v1annealTT_merge3_116k_120k,include_base_44_polish_stem,0,lm-eval,vllm,,acc,none,0.2708333333333333,0.06482097094483914,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/63ed3cabf3_2026-10-07T15-53-08.736481.json,1791388226.89617,1 +v1annealTT_merge3_116k_120k,include_base_44_portuguese,0,lm-eval,vllm,yes,acc,none,0.6188747731397459,0.020398897271901896,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ae84e610a_2026-10-07T15-48-53.891204.json,1791387971.9874203,1 +v1annealTT_merge3_116k_120k,include_base_44_portuguese_applied_science,0,lm-eval,vllm,,acc,none,0.6071428571428571,0.05360727429546049,84,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ae84e610a_2026-10-07T15-48-53.891204.json,1791387971.9874203,1 +v1annealTT_merge3_116k_120k,include_base_44_portuguese_arts_humanities,0,lm-eval,vllm,,acc,none,0.6428571428571429,0.03873758175333146,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ae84e610a_2026-10-07T15-48-53.891204.json,1791387971.9874203,1 +v1annealTT_merge3_116k_120k,include_base_44_portuguese_business_commerce,0,lm-eval,vllm,,acc,none,0.3888888888888889,0.057855371034784636,72,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ae84e610a_2026-10-07T15-48-53.891204.json,1791387971.9874203,1 +v1annealTT_merge3_116k_120k,include_base_44_portuguese_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6451612903225806,0.06126109130650273,62,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ae84e610a_2026-10-07T15-48-53.891204.json,1791387971.9874203,1 +v1annealTT_merge3_116k_120k,include_base_44_portuguese_social_science,0,lm-eval,vllm,,acc,none,0.7012987012987013,0.0370019283065312,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ae84e610a_2026-10-07T15-48-53.891204.json,1791387971.9874203,1 +v1annealTT_merge3_116k_120k,include_base_44_portuguese_stem,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ae84e610a_2026-10-07T15-48-53.891204.json,1791387971.9874203,1 +v1annealTT_merge3_116k_120k,include_base_44_serbian,0,lm-eval,vllm,yes,acc,none,0.7054545454545454,0.01935189324143919,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0587175f54_2026-10-07T15-50-56.801973.json,1791388095.5612123,1 +v1annealTT_merge3_116k_120k,include_base_44_serbian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6645367412140575,0.026730352285433724,313,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0587175f54_2026-10-07T15-50-56.801973.json,1791388095.5612123,1 +v1annealTT_merge3_116k_120k,include_base_44_serbian_social_science,0,lm-eval,vllm,,acc,none,0.7807486631016043,0.030336835568230927,187,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0587175f54_2026-10-07T15-50-56.801973.json,1791388095.5612123,1 +v1annealTT_merge3_116k_120k,include_base_44_serbian_stem,0,lm-eval,vllm,,acc,none,0.68,0.06663945022680344,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0587175f54_2026-10-07T15-50-56.801973.json,1791388095.5612123,1 +v1annealTT_merge3_116k_120k,include_base_44_spanish,0,lm-eval,vllm,yes,acc,none,0.6727272727272727,0.019748670588421644,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72f754e0af_2026-10-07T15-44-41.503743.json,1791387722.7695193,1 +v1annealTT_merge3_116k_120k,include_base_44_spanish_arts_humanities,0,lm-eval,vllm,,acc,none,0.584,0.031235856237014505,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72f754e0af_2026-10-07T15-44-41.503743.json,1791387722.7695193,1 +v1annealTT_merge3_116k_120k,include_base_44_spanish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72f754e0af_2026-10-07T15-44-41.503743.json,1791387722.7695193,1 +v1annealTT_merge3_116k_120k,include_base_44_spanish_social_science,0,lm-eval,vllm,,acc,none,0.752,0.027367497504863593,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72f754e0af_2026-10-07T15-44-41.503743.json,1791387722.7695193,1 +v1annealTT_merge3_116k_120k,include_base_44_spanish_stem,0,lm-eval,vllm,,acc,none,0.8,0.08164965809277261,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72f754e0af_2026-10-07T15-44-41.503743.json,1791387722.7695193,1 +v1annealTT_merge3_116k_120k,include_base_44_turkish,0,lm-eval,vllm,yes,acc,none,0.5748175182481752,0.02060733118023825,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/114ec96f0e_2026-10-07T15-44-44.671371.json,1791387724.8607633,1 +v1annealTT_merge3_116k_120k,include_base_44_turkish_arts_humanities,0,lm-eval,vllm,,acc,none,0.5481927710843374,0.0387437155658795,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/114ec96f0e_2026-10-07T15-44-44.671371.json,1791387724.8607633,1 +v1annealTT_merge3_116k_120k,include_base_44_turkish_business_commerce,0,lm-eval,vllm,,acc,none,0.7228915662650602,0.03484331592680584,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/114ec96f0e_2026-10-07T15-44-44.671371.json,1791387724.8607633,1 +v1annealTT_merge3_116k_120k,include_base_44_turkish_social_science,0,lm-eval,vllm,,acc,none,0.5301204819277109,0.03885425420866771,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/114ec96f0e_2026-10-07T15-44-44.671371.json,1791387724.8607633,1 +v1annealTT_merge3_116k_120k,include_base_44_turkish_stem,0,lm-eval,vllm,,acc,none,0.32,0.06663945022680343,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/114ec96f0e_2026-10-07T15-44-44.671371.json,1791387724.8607633,1 +v1annealTT_merge3_116k_120k,include_base_44_ukrainian,0,lm-eval,vllm,yes,acc,none,0.6472727272727272,0.02042916638751278,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4498558ab5_2026-10-07T15-47-07.268653.json,1791387863.915429,1 +v1annealTT_merge3_116k_120k,include_base_44_ukrainian_arts_humanities,0,lm-eval,vllm,,acc,none,0.648,0.030266288057359866,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4498558ab5_2026-10-07T15-47-07.268653.json,1791387863.915429,1 +v1annealTT_merge3_116k_120k,include_base_44_ukrainian_social_science,0,lm-eval,vllm,,acc,none,0.644,0.0303436806571532,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4498558ab5_2026-10-07T15-47-07.268653.json,1791387863.915429,1 +v1annealTT_merge3_116k_120k,include_base_44_ukrainian_stem,0,lm-eval,vllm,,acc,none,0.66,0.0676726816132972,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4498558ab5_2026-10-07T15-47-07.268653.json,1791387863.915429,1 +v1annealTT_merge3_116k_120k,jeopardy,10,lm-eval,vllm,,exact_match,strict-match,0.5418044402456306,0.010831507041499497,2117,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b0ec956cc_2026-10-07T15-53-36.987204.json,1791388218.7394736,1 +v1annealTT_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,acc,none,0.7302542208422278,0.006183387157849211,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7eafbbc4d3_2026-10-07T15-53-24.638986.json,1791388218.4484427,1 +v1annealTT_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,perplexity,none,3.4752432650098695,0.06768453982661783,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7eafbbc4d3_2026-10-07T15-53-24.638986.json,1791388218.4484427,1 +v1annealTT_merge3_116k_120k,mbpp,3,lm-eval,vllm,,pass_at_1,none,0.626,0.02166071034720448,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3f080bfada_2026-10-07T15-49-18.321533.json,1791387972.2166085,1 +v1annealTT_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.72,0.02845414827783232,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a12e23709_2026-10-07T16-19-35.765668.json,1791389803.3471875,1 +v1annealTT_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,strict-match,0.772,0.026587432487268477,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a12e23709_2026-10-07T16-19-35.765668.json,1791389803.3471875,1 +v1annealTT_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.792,0.025721398901416392,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/13296641a9_2026-10-07T15-42-59.552621.json,1791387598.7730422,1 +v1annealTT_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,strict-match,0.74,0.027797315752644304,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/13296641a9_2026-10-07T15-42-59.552621.json,1791387598.7730422,1 +v1annealTT_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.816,0.02455581299422256,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/66542a21d2_2026-10-07T15-49-08.133901.json,1791387971.9183667,1 +v1annealTT_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,strict-match,0.732,0.028068762382526688,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/66542a21d2_2026-10-07T15-49-08.133901.json,1791387971.9183667,1 +v1annealTT_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.704,0.028928939388379635,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b0ba06be5f_2026-10-07T15-53-07.414983.json,1791388211.198894,1 +v1annealTT_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,strict-match,0.768,0.026750070374865164,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b0ba06be5f_2026-10-07T15-53-07.414983.json,1791388211.198894,1 +v1annealTT_merge3_116k_120k,mmlu,5,lm-eval,vllm,yes,acc,none,0.7378578550064093,0.0035571619806653203,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_abstract_algebra,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_anatomy,5,lm-eval,vllm,,acc,none,0.6518518518518519,0.04115324610336956,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_business_ethics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.769811320754717,0.02590789712240816,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_college_biology,5,lm-eval,vllm,,acc,none,0.8402777777777778,0.030635578972093305,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_college_computer_science,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_college_mathematics,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_college_medicine,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.033687629322594316,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_college_physics,5,lm-eval,vllm,,acc,none,0.5686274509803921,0.049280995972875316,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_computer_security,5,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7872340425531915,0.02675439134803978,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_econometrics,5,lm-eval,vllm,,acc,none,0.6491228070175439,0.044895393502707,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7517241379310344,0.03600105692727776,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.7142857142857143,0.02326651221373058,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_formal_logic,5,lm-eval,vllm,,acc,none,0.7063492063492064,0.040735243221471276,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_global_facts,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_biology,5,lm-eval,vllm,,acc,none,0.8935483870967742,0.017545102951656674,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.7044334975369458,0.03210494433751457,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_geography,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.02239078763821682,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9533678756476683,0.015216761819262604,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7846153846153846,0.02084303455746285,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5185185185185185,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8865546218487395,0.020600225750204797,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_physics,5,lm-eval,vllm,,acc,none,0.609271523178808,0.039837983066598075,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_psychology,5,lm-eval,vllm,,acc,none,0.9045871559633027,0.012595899282335761,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7268518518518519,0.030388051301678112,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8725490196078431,0.02340553048084634,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_high_school_world_history,5,lm-eval,vllm,,acc,none,0.890295358649789,0.02034340073486879,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_human_aging,5,lm-eval,vllm,,acc,none,0.7802690582959642,0.027790177064383567,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_human_sexuality,5,lm-eval,vllm,,acc,none,0.8473282442748091,0.031545216720054704,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_humanities,5,lm-eval,vllm,yes,acc,none,0.6850159404888416,0.006497250565449624,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_jurisprudence,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.03602814176392641,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7975460122699386,0.031570650789119054,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_machine_learning,5,lm-eval,vllm,,acc,none,0.6696428571428571,0.04464285714285714,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_management,5,lm-eval,vllm,,acc,none,0.8446601941747572,0.03586594738573976,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_marketing,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.02058849131609242,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_medical_genetics,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_miscellaneous,5,lm-eval,vllm,,acc,none,0.8480204342273308,0.012837852506645289,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_moral_disputes,5,lm-eval,vllm,,acc,none,0.7976878612716763,0.021628077380196193,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5374301675977654,0.01667557868730807,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_nutrition,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.024630048979824716,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_other,5,lm-eval,vllm,yes,acc,none,0.7557129063405214,0.007459224009676195,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_philosophy,5,lm-eval,vllm,,acc,none,0.7620578778135049,0.02418515064781868,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_prehistory,5,lm-eval,vllm,,acc,none,0.8179012345679012,0.02147349183480832,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_professional_accounting,5,lm-eval,vllm,,acc,none,0.5673758865248227,0.029555454236778838,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_professional_law,5,lm-eval,vllm,,acc,none,0.5743155149934811,0.01262839355181204,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_professional_medicine,5,lm-eval,vllm,,acc,none,0.7389705882352942,0.026679252270103055,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_professional_psychology,5,lm-eval,vllm,,acc,none,0.7794117647058824,0.01677467236546851,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_security_studies,5,lm-eval,vllm,,acc,none,0.7673469387755102,0.02704925791589615,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_social_sciences,5,lm-eval,vllm,yes,acc,none,0.834579135521612,0.006562403299746393,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_sociology,5,lm-eval,vllm,,acc,none,0.9054726368159204,0.020687186951534122,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_stem,5,lm-eval,vllm,yes,acc,none,0.7047256581033936,0.007869212915281113,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.91,0.028762349126466136,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_virology,5,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,mmlu_world_religions,5,lm-eval,vllm,,acc,none,0.847953216374269,0.027539122889061483,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5bc7c20aad_2026-10-07T16-14-23.387103.json,1791389324.9133294,1 +v1annealTT_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc,none,0.9792514239218877,0.0028756675478370194,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9c82154e61_2026-10-07T16-17-29.851559.json,1791389685.213956,1 +v1annealTT_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc_norm,none,0.9772172497965825,0.0030102048992459093,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9c82154e61_2026-10-07T16-17-29.851559.json,1791389685.213956,1 +v1annealTT_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc,none,0.9807355516637478,0.002876744504272351,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/25a744449c_2026-10-07T16-11-38.650787.json,1791389324.2691224,1 +v1annealTT_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc_norm,none,0.9776707530647986,0.0030922912692911255,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/25a744449c_2026-10-07T16-11-38.650787.json,1791389324.2691224,1 +v1annealTT_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc,none,0.9696898496240601,0.00262821378044209,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b24932d51c_2026-10-07T16-17-39.054257.json,1791389670.8189957,1 +v1annealTT_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc_norm,none,0.9659304511278195,0.0027810342534106158,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b24932d51c_2026-10-07T16-17-39.054257.json,1791389670.8189957,1 +v1annealTT_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a5f86317c_2026-10-07T15-50-42.209471.json,1791388096.058488,1 +v1annealTT_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a5f86317c_2026-10-07T15-50-42.209471.json,1791388096.058488,1 +v1annealTT_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc,none,0.9882506527415144,0.00224832933645723,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f97b684377_2026-10-07T15-49-01.171503.json,1791387970.6656146,1 +v1annealTT_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc_norm,none,0.9878154917319408,0.0022890823793506295,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f97b684377_2026-10-07T15-49-01.171503.json,1791387970.6656146,1 +v1annealTT_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc,none,0.9945255474452555,0.0022298274651133573,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8d4e2555f1_2026-10-07T15-42-36.948893.json,1791387587.59578,1 +v1annealTT_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc_norm,none,0.9927007299270073,0.002572419703677233,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8d4e2555f1_2026-10-07T15-42-36.948893.json,1791387587.59578,1 +v1annealTT_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc,none,0.9961038961038962,0.0022464896096721586,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c8a9bc7117_2026-10-07T16-17-10.958760.json,1791389684.7097542,1 +v1annealTT_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc_norm,none,0.9896103896103896,0.003656525311609037,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c8a9bc7117_2026-10-07T16-17-10.958760.json,1791389684.7097542,1 +v1annealTT_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc,none,0.9332038834951456,0.004921070696565147,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b9d7c0e0cb_2026-10-07T15-36-37.418717.json,1791387225.0914798,1 +v1annealTT_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc_norm,none,0.9355339805825242,0.004840507968021292,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b9d7c0e0cb_2026-10-07T15-36-37.418717.json,1791387225.0914798,1 +v1annealTT_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc,none,0.989010989010989,0.006321140017972834,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/baeb706886_2026-10-07T15-46-38.369912.json,1791387863.7562847,1 +v1annealTT_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc_norm,none,0.7216117216117216,0.027176455318754105,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/baeb706886_2026-10-07T15-46-38.369912.json,1791387863.7562847,1 +v1annealTT_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc,none,0.9575875486381323,0.003976068706087139,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9e43facdc_2026-10-07T15-48-50.661025.json,1791387964.2648664,1 +v1annealTT_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc_norm,none,0.9521400778210116,0.004211670287747304,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9e43facdc_2026-10-07T15-48-50.661025.json,1791387964.2648664,1 +v1annealTT_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc,none,0.9913657770800628,0.0018332180191281344,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17d7231d1b_2026-10-07T15-44-46.789539.json,1791387718.9000103,1 +v1annealTT_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc_norm,none,0.9886185243328101,0.0021018377434555546,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/17d7231d1b_2026-10-07T15-44-46.789539.json,1791387718.9000103,1 +v1annealTT_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc,none,0.8928571428571429,0.05952380952380952,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/90ed3fc706_2026-10-07T16-17-04.920659.json,1791389690.8887599,1 +v1annealTT_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc_norm,none,0.8214285714285714,0.07370704611510599,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/90ed3fc706_2026-10-07T16-17-04.920659.json,1791389690.8887599,1 +v1annealTT_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc,none,0.9747675962815405,0.005719011027184107,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72170a262d_2026-10-07T16-15-08.025627.json,1791389557.8941789,1 +v1annealTT_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc_norm,none,0.9588313413014609,0.007245119435705399,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72170a262d_2026-10-07T16-15-08.025627.json,1791389557.8941789,1 +v1annealTT_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc,none,0.9881314668289713,0.0018894621730315584,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f50fc28d43_2026-10-07T15-53-40.270935.json,1791388222.453931,1 +v1annealTT_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc_norm,none,0.9887401095556908,0.0018409435499718771,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f50fc28d43_2026-10-07T15-53-40.270935.json,1791388222.453931,1 +v1annealTT_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc,none,0.9857988165680474,0.004072725984449868,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/54bbe61221_2026-10-07T15-44-25.738237.json,1791387718.4373686,1 +v1annealTT_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc_norm,none,0.9822485207100592,0.004545239198936023,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/54bbe61221_2026-10-07T15-44-25.738237.json,1791387718.4373686,1 +v1annealTT_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc,none,0.9821492324169939,0.002502293068346338,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/350c8ba6b4_2026-10-07T15-49-09.264076.json,1791387973.2133777,1 +v1annealTT_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc_norm,none,0.9760799714387719,0.0028876498597387714,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/350c8ba6b4_2026-10-07T15-49-09.264076.json,1791387973.2133777,1 +v1annealTT_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc,none,0.9669889963321107,0.0032630544153682763,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d19cd2af16_2026-10-07T16-15-37.560529.json,1791389556.5888293,1 +v1annealTT_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc_norm,none,0.9576525508502834,0.00367791593303643,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d19cd2af16_2026-10-07T16-15-37.560529.json,1791389556.5888293,1 +v1annealTT_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc,none,0.9607843137254902,0.013623692819208846,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72d5a71935_2026-10-07T16-17-21.791018.json,1791389684.590285,1 +v1annealTT_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc_norm,none,0.8872549019607843,0.022198571039456782,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/72d5a71935_2026-10-07T16-17-21.791018.json,1791389684.590285,1 +v1annealTT_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc,none,0.9686675461741425,0.0031644017117049552,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3fcc00c7aa_2026-10-07T15-49-20.587252.json,1791387965.9638104,1 +v1annealTT_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc_norm,none,0.9640501319261213,0.003381469631995044,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3fcc00c7aa_2026-10-07T15-49-20.587252.json,1791387965.9638104,1 +v1annealTT_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc,none,0.9805084745762712,0.004026166098461977,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e2a927300e_2026-10-07T15-44-36.374535.json,1791387722.135486,1 +v1annealTT_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc_norm,none,0.9779661016949153,0.004275143220925853,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e2a927300e_2026-10-07T15-44-36.374535.json,1791387722.135486,1 +v1annealTT_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/eaff6a9ba6_2026-10-07T15-52-24.774480.json,1791388209.4078763,1 +v1annealTT_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/eaff6a9ba6_2026-10-07T15-52-24.774480.json,1791388209.4078763,1 +v1annealTT_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc,none,0.9695409695409696,0.0035601078926196664,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4c613a48a7_2026-10-07T15-47-03.467263.json,1791387856.290154,1 +v1annealTT_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc_norm,none,0.9566709566709567,0.004217867030732631,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4c613a48a7_2026-10-07T15-47-03.467263.json,1791387856.290154,1 +v1annealTT_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc,none,0.9731051344743277,0.0028286179860137497,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2ded5a8bea_2026-10-07T15-51-03.631309.json,1791388093.8466165,1 +v1annealTT_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc_norm,none,0.9562958435207825,0.0035745159002332585,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2ded5a8bea_2026-10-07T15-51-03.631309.json,1791388093.8466165,1 +v1annealTT_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc,none,0.9757217847769029,0.0027882720939083226,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ecd9ae8c9_2026-10-07T15-44-45.901365.json,1791387714.2639353,1 +v1annealTT_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc_norm,none,0.9757217847769029,0.0027882720939083226,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ecd9ae8c9_2026-10-07T15-44-45.901365.json,1791387714.2639353,1 +v1annealTT_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc,none,0.9732490272373541,0.0035593923740515725,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d337ff51fe_2026-10-07T15-44-41.677616.json,1791387720.8364625,1 +v1annealTT_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc_norm,none,0.9693579766536965,0.0038018493227979736,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d337ff51fe_2026-10-07T15-44-41.677616.json,1791387720.8364625,1 +v1annealTT_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc,none,0.9688781664656212,0.0026974741962687986,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/871d11fb28_2026-10-07T15-38-41.952247.json,1791387350.736698,1 +v1annealTT_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc_norm,none,0.9640530759951749,0.0028918213898218846,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/871d11fb28_2026-10-07T15-38-41.952247.json,1791387350.736698,1 +v1annealTT_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc,none,0.9504795895605621,0.0032406161300864394,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7f69cb4e0a_2026-10-07T16-12-00.337662.json,1791389318.4019384,1 +v1annealTT_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc_norm,none,0.9444568369395494,0.0034211367597077372,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7f69cb4e0a_2026-10-07T16-12-00.337662.json,1791389318.4019384,1 +v1annealTT_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc,none,0.9815033451397088,0.002673471939690263,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93baea1913_2026-10-07T16-21-45.519876.json,1791389927.2713118,1 +v1annealTT_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc_norm,none,0.9822904368358913,0.0026170198938226304,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93baea1913_2026-10-07T16-21-45.519876.json,1791389927.2713118,1 +v1annealTT_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc,none,0.9794238683127572,0.009125559983277567,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d1379ed0bc_2026-10-07T15-38-05.212839.json,1791387345.7731912,1 +v1annealTT_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc_norm,none,0.9588477366255144,0.012769209252432483,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d1379ed0bc_2026-10-07T15-38-05.212839.json,1791387345.7731912,1 +v1annealTT_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc,none,0.9900497512437811,0.007018276606798947,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2372e190ac_2026-10-07T15-50-33.078304.json,1791388095.1021764,1 +v1annealTT_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc_norm,none,0.9900497512437811,0.007018276606798947,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2372e190ac_2026-10-07T15-50-33.078304.json,1791388095.1021764,1 +v1annealTT_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc,none,0.9414466130884042,0.005626968366702607,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b153a80109_2026-10-07T15-46-52.805139.json,1791387860.4497895,1 +v1annealTT_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc_norm,none,0.8949483352468427,0.007348540063180247,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b153a80109_2026-10-07T15-46-52.805139.json,1791387860.4497895,1 +v1annealTT_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc,none,0.9766763848396501,0.0028817770153826625,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ff6002e52_2026-10-07T15-44-54.228241.json,1791387722.1417234,1 +v1annealTT_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc_norm,none,0.9690233236151603,0.0033080466145895965,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ff6002e52_2026-10-07T15-44-54.228241.json,1791387722.1417234,1 +v1annealTT_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc,none,0.348,0.021323728632807425,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0cd5a7d86b_2026-10-07T15-50-54.541804.json,1791388090.5823278,1 +v1annealTT_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc_norm,none,0.466,0.022331264423258324,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0cd5a7d86b_2026-10-07T15-50-54.541804.json,1791388090.5823278,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,bleu,none,18.333916900131886,0.2680719890056358,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/18cf0a8807_2026-10-07T15-50-48.011439.json,1791387970.5415013,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,chrf,none,38.51131122867645,0.25665570641114643,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/18cf0a8807_2026-10-07T15-50-48.011439.json,1791387970.5415013,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,bleu,none,25.659606046602157,0.27579237447660765,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7574b14ff9_2026-10-07T15-50-53.711829.json,1791387969.7441533,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,chrf,none,44.62249935493018,0.23323379556453339,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7574b14ff9_2026-10-07T15-50-53.711829.json,1791387969.7441533,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,bleu,none,30.87984134299721,0.3264322204812727,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/411df83727_2026-10-07T15-38-26.726528.json,1791387227.4687016,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,chrf,none,50.056796372658496,0.26951973406365837,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/411df83727_2026-10-07T15-38-26.726528.json,1791387227.4687016,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,bleu,none,28.45251969937237,0.2992318331703258,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7a01556475_2026-10-07T15-46-50.265872.json,1791387722.0249755,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,chrf,none,48.88772616937147,0.2426939943054216,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7a01556475_2026-10-07T15-46-50.265872.json,1791387722.0249755,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,bleu,none,29.886075621018787,0.33212113009499605,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c033691fb9_2026-10-07T16-19-46.515462.json,1791389684.176775,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,chrf,none,48.287692829429304,0.2740328035004121,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c033691fb9_2026-10-07T16-19-46.515462.json,1791389684.176775,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,bleu,none,13.580732583712212,0.26296171925698036,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3d177a6b0d_2026-10-07T15-46-46.490174.json,1791387721.5317311,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,chrf,none,39.99819643399786,0.26776642811752777,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3d177a6b0d_2026-10-07T15-46-46.490174.json,1791387721.5317311,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,bleu,none,17.71378357316197,0.3283584413029355,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/14f6fdd355_2026-10-07T15-49-09.157654.json,1791387863.873152,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,chrf,none,40.467259015457884,0.27589582930228274,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/14f6fdd355_2026-10-07T15-49-09.157654.json,1791387863.873152,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,bleu,none,30.023980680098585,0.3231263916723316,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e2d3cec4ce_2026-10-07T15-49-13.122177.json,1791387859.2693815,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,chrf,none,52.11217874744786,0.2381201280528088,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e2d3cec4ce_2026-10-07T15-49-13.122177.json,1791387859.2693815,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,bleu,none,23.686593277115133,0.2989936689747421,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/535c7705f2_2026-10-07T16-13-35.641286.json,1791389311.2207465,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,chrf,none,48.847415179733666,0.27789421242648454,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/535c7705f2_2026-10-07T16-13-35.641286.json,1791389311.2207465,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,bleu,none,24.525884683442793,0.336840648737486,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51684f82f5_2026-10-07T16-19-44.036525.json,1791389683.056703,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,chrf,none,48.190900689751786,0.30659299011597535,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51684f82f5_2026-10-07T16-19-44.036525.json,1791389683.056703,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,bleu,none,29.03132124830231,0.34361769827284633,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/867c492f62_2026-10-07T15-51-05.772028.json,1791387972.8532188,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,chrf,none,52.0826203991982,0.286151429957566,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/867c492f62_2026-10-07T15-51-05.772028.json,1791387972.8532188,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,bleu,none,21.99068141999363,0.3522771110884535,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/32af4d92d0_2026-10-07T15-55-05.981462.json,1791388219.871629,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,chrf,none,46.74901553652854,0.26084262312825385,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/32af4d92d0_2026-10-07T15-55-05.981462.json,1791388219.871629,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,bleu,none,16.88246003116528,0.3376263573039017,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/138fa4a4ff_2026-10-07T16-13-20.357414.json,1791389310.3011715,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,chrf,none,46.538320480137635,0.2693845479399865,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/138fa4a4ff_2026-10-07T16-13-20.357414.json,1791389310.3011715,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,bleu,none,16.876982948456316,0.23385990025432832,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3b06b895fe_2026-10-07T15-46-59.668445.json,1791387722.730269,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,chrf,none,44.287685289971115,0.2551403522929839,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3b06b895fe_2026-10-07T15-46-59.668445.json,1791387722.730269,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,bleu,none,24.58873980298069,0.38441238907581965,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2aa872e161_2026-10-07T15-38-34.092406.json,1791387231.9132116,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,chrf,none,52.04136416988199,0.29066889168230553,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2aa872e161_2026-10-07T15-38-34.092406.json,1791387231.9132116,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,bleu,none,16.92586020150753,0.31843503046876437,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83617ae835_2026-10-07T15-55-16.749800.json,1791388218.9018419,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,chrf,none,39.98641721784045,0.25607394785877613,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83617ae835_2026-10-07T15-55-16.749800.json,1791388218.9018419,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,bleu,none,28.099381363701465,0.3955004799004882,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4d3b99ffb7_2026-10-07T16-17-28.865360.json,1791389564.9676468,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,chrf,none,51.728378186476135,0.25266941228584056,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4d3b99ffb7_2026-10-07T16-17-28.865360.json,1791389564.9676468,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,bleu,none,18.555656157774603,0.3084980181603869,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d1f150a917_2026-10-07T15-52-58.364652.json,1791388087.234557,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,chrf,none,42.81697599268172,0.24224012867878875,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d1f150a917_2026-10-07T15-52-58.364652.json,1791388087.234557,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,bleu,none,20.638781242662123,0.342505241642739,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3f1f89dd0_2026-10-07T15-53-21.507958.json,1791388095.4652646,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,chrf,none,44.15793619290569,0.26056376559968153,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3f1f89dd0_2026-10-07T15-53-21.507958.json,1791388095.4652646,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,bleu,none,20.444478263690133,0.2854567369196877,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ffbc0b4ac4_2026-10-07T15-53-02.610644.json,1791388093.6490955,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,chrf,none,46.644598529128025,0.2466567048019559,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ffbc0b4ac4_2026-10-07T15-53-02.610644.json,1791388093.6490955,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,bleu,none,31.77452189067481,0.32429607581812536,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7f7b9d91ce_2026-10-07T15-44-43.878664.json,1791387600.2086313,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,chrf,none,55.62008288818397,0.2871914641357607,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7f7b9d91ce_2026-10-07T15-44-43.878664.json,1791387600.2086313,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,bleu,none,20.600553372666155,0.3725501853049116,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cf7f2a8e5a_2026-10-07T15-44-49.356883.json,1791387602.1839228,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,chrf,none,45.708314208359255,0.30327291771322556,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cf7f2a8e5a_2026-10-07T15-44-49.356883.json,1791387602.1839228,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,bleu,none,24.852494779948046,0.3007856622361628,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f29db14e00_2026-10-07T15-40-33.076963.json,1791387347.8027735,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,chrf,none,51.19851491661548,0.26826342936203507,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f29db14e00_2026-10-07T15-40-33.076963.json,1791387347.8027735,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,bleu,none,26.653145033261726,0.362317776767947,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bef89c086d_2026-10-07T16-22-01.341498.json,1791389816.1690738,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,chrf,none,51.54144704312086,0.27318211969192907,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bef89c086d_2026-10-07T16-22-01.341498.json,1791389816.1690738,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,bleu,none,24.631445474354358,0.36052277925917914,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b75de48fc5_2026-10-07T15-55-12.002403.json,1791388218.5682306,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,chrf,none,47.31114944814061,0.24620224432547227,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b75de48fc5_2026-10-07T15-55-12.002403.json,1791388218.5682306,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,bleu,none,15.26577585226433,0.26452253185722446,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fcdcc9decd_2026-10-07T15-44-29.858702.json,1791387588.3625531,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,chrf,none,41.81233299941667,0.2435879543370012,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fcdcc9decd_2026-10-07T15-44-29.858702.json,1791387588.3625531,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,bleu,none,19.77421883651707,0.3332972266138402,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aadbc06400_2026-10-07T15-47-09.863536.json,1791387721.5002744,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,chrf,none,40.215185911538704,0.46639217853197423,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aadbc06400_2026-10-07T15-47-09.863536.json,1791387721.5002744,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,bleu,none,34.44415770686107,0.36002028402722047,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/757a40512e_2026-10-07T16-19-28.617005.json,1791389684.0302975,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,chrf,none,55.372198610416746,0.2992785738303131,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/757a40512e_2026-10-07T16-19-28.617005.json,1791389684.0302975,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,bleu,none,20.2097949081166,0.3523658715371152,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/96efc10c53_2026-10-07T15-52-54.652587.json,1791388088.932928,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,chrf,none,48.61213324623047,0.28197987263119556,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/96efc10c53_2026-10-07T15-52-54.652587.json,1791388088.932928,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,bleu,none,17.23980223868075,0.26890831743305893,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/760c0409fa_2026-10-07T16-23-49.612405.json,1791389933.4887314,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,chrf,none,38.9284600023362,0.25101776679823157,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/760c0409fa_2026-10-07T16-23-49.612405.json,1791389933.4887314,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,bleu,none,32.07917074920783,0.31780244191595897,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b009fc9088_2026-10-07T15-47-08.258305.json,1791387723.914313,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,chrf,none,51.015711701851465,0.2650023627869509,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b009fc9088_2026-10-07T15-47-08.258305.json,1791387723.914313,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,bleu,none,29.550721905352233,0.33013119928699186,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3e33a0fb02_2026-10-07T15-46-45.994972.json,1791387726.709899,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,chrf,none,48.44610041795183,0.25580898635324595,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3e33a0fb02_2026-10-07T15-46-45.994972.json,1791387726.709899,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,bleu,none,24.046100237270053,0.3141698670797049,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6b757c2640_2026-10-07T15-46-41.284713.json,1791387723.4397094,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,chrf,none,44.09477197880694,0.2606873329642538,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6b757c2640_2026-10-07T15-46-41.284713.json,1791387723.4397094,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,bleu,none,19.58642395844596,0.2784277813604321,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9c47e24499_2026-10-07T15-52-39.252936.json,1791388091.290754,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,chrf,none,39.30902364564229,0.25468843451353235,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9c47e24499_2026-10-07T15-52-39.252936.json,1791388091.290754,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,bleu,none,31.111585049210124,0.39338940790364674,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e56fc8ed03_2026-10-07T16-21-31.222580.json,1791389804.1412568,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,chrf,none,51.26436010981287,0.3162218074014067,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e56fc8ed03_2026-10-07T16-21-31.222580.json,1791389804.1412568,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,bleu,none,23.656602485025296,0.29219647147458094,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f73fbb9a5_2026-10-07T15-46-45.211694.json,1791387719.9156551,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,chrf,none,42.5197064465695,0.23372234849217807,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f73fbb9a5_2026-10-07T15-46-45.211694.json,1791387719.9156551,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,bleu,none,32.687286047176485,0.313730512438146,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/86c1086c98_2026-10-07T15-40-40.218325.json,1791387347.8447423,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,chrf,none,50.79534492805936,0.25608091741831784,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/86c1086c98_2026-10-07T15-40-40.218325.json,1791387347.8447423,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,bleu,none,27.38914214783384,0.35828477127286823,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fe974176f4_2026-10-07T15-46-51.941534.json,1791387722.3915694,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,chrf,none,45.522215504325324,0.2765028668742677,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fe974176f4_2026-10-07T15-46-51.941534.json,1791387722.3915694,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,bleu,none,28.723992024253878,0.3294645059989598,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/24ec008cb9_2026-10-07T16-19-34.504708.json,1791389688.5948167,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,chrf,none,47.35704188614061,0.2667902517931835,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/24ec008cb9_2026-10-07T16-19-34.504708.json,1791389688.5948167,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,bleu,none,23.689446095384326,0.3012073349464474,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99705c77f1_2026-10-07T16-23-31.360180.json,1791389922.989099,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,chrf,none,43.016641330651495,0.2472362216182078,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/99705c77f1_2026-10-07T16-23-31.360180.json,1791389922.989099,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,bleu,none,32.05764971694677,0.3160664853932103,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f266d1c2ea_2026-10-07T15-52-53.301157.json,1791388091.069924,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,chrf,none,50.90576303405222,0.27057673368429475,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f266d1c2ea_2026-10-07T15-52-53.301157.json,1791388091.069924,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,bleu,none,27.129199926162844,0.3086506443493248,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d4d5130818_2026-10-07T15-53-00.700126.json,1791388098.2329168,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,chrf,none,46.28292677552119,0.2570156887314879,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d4d5130818_2026-10-07T15-53-00.700126.json,1791388098.2329168,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,bleu,none,34.91296414582983,0.3486363400917822,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3872f53795_2026-10-07T15-46-57.594748.json,1791387726.4812627,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,chrf,none,53.35819360564209,0.270304229766362,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3872f53795_2026-10-07T15-46-57.594748.json,1791387726.4812627,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,bleu,none,34.20520158886476,0.3818528740614301,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d7228c567_2026-10-07T15-49-16.873579.json,1791387866.1599376,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,chrf,none,52.010068590763716,0.2932875579491552,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1d7228c567_2026-10-07T15-49-16.873579.json,1791387866.1599376,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,bleu,none,33.106391753481326,0.3355142980045513,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bbc92ef34a_2026-10-07T16-19-27.470812.json,1791389684.3026524,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,chrf,none,50.87014171540558,0.2653696283948355,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bbc92ef34a_2026-10-07T16-19-27.470812.json,1791389684.3026524,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,bleu,none,21.768569620465136,0.2634682135041985,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bad40575b6_2026-10-07T16-19-44.037680.json,1791389685.8355887,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,chrf,none,41.50822097844385,0.2328378898649971,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bad40575b6_2026-10-07T16-19-44.037680.json,1791389685.8355887,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,bleu,none,32.269820251635586,0.35523856154073336,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2461c422bf_2026-10-07T16-23-37.929816.json,1791389923.185111,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,chrf,none,53.020941503402454,0.27067361867272205,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2461c422bf_2026-10-07T16-23-37.929816.json,1791389923.185111,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,bleu,none,38.2263497585496,0.3401116221807815,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4726f4c2e4_2026-10-07T15-38-32.059015.json,1791387225.1288784,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,chrf,none,55.353408249913926,0.2751305483991281,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4726f4c2e4_2026-10-07T15-38-32.059015.json,1791387225.1288784,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,bleu,none,29.34508259497156,0.29926202259496437,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0614e7e5f9_2026-10-07T15-46-50.334420.json,1791387724.871478,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,chrf,none,49.07665530926315,0.275850828538471,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0614e7e5f9_2026-10-07T15-46-50.334420.json,1791387724.871478,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,bleu,none,25.172077463280736,0.3082055269086965,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8dddb4a59_2026-10-07T15-51-00.133414.json,1791387970.5474503,1 +v1annealTT_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,chrf,none,44.14387730451671,0.24116297692812672,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8dddb4a59_2026-10-07T15-51-00.133414.json,1791387970.5474503,1 +v1annealTT_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc,none,0.8057671381936888,0.00923020936616823,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7a88d7e37d_2026-10-07T16-21-39.348778.json,1791389935.6028223,1 +v1annealTT_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc_norm,none,0.8166485310119695,0.0090282839846894,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7a88d7e37d_2026-10-07T16-21-39.348778.json,1791389935.6028223,1 +v1annealTT_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc,none,0.8210010881392819,0.00894422022020486,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dabcc401ec_2026-10-07T16-11-47.510843.json,1791389317.448322,1 +v1annealTT_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc_norm,none,0.8373231773667029,0.008611024380872861,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dabcc401ec_2026-10-07T16-11-47.510843.json,1791389317.448322,1 +v1annealTT_merge3_116k_120k,polymath_de_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/89a264a0d9_2026-10-07T15-38-58.273574.json,1791387352.5073493,1 +v1annealTT_merge3_116k_120k,polymath_de_low,0,lm-eval,vllm,,exact_match,none,0.248,0.03878143885933063,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/755112faf3_2026-10-07T16-17-42.612606.json,1791389683.3338614,1 +v1annealTT_merge3_116k_120k,polymath_de_medium,0,lm-eval,vllm,,exact_match,none,0.104,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a6a93b6295_2026-10-07T15-36-57.113807.json,1791387221.8135026,1 +v1annealTT_merge3_116k_120k,polymath_de_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d12ff9bee5_2026-10-07T15-53-25.593722.json,1791388221.5786235,1 +v1annealTT_merge3_116k_120k,polymath_en_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/739b91f5b0_2026-10-07T15-45-04.507705.json,1791387723.3304985,1 +v1annealTT_merge3_116k_120k,polymath_en_low,0,lm-eval,vllm,,exact_match,none,0.064,0.02197946255470202,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0b05cb2993_2026-10-07T16-11-38.849033.json,1791389316.7403717,1 +v1annealTT_merge3_116k_120k,polymath_en_medium,0,lm-eval,vllm,,exact_match,none,0.08,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0d9df1f6b0_2026-10-07T15-51-16.929822.json,1791388090.392726,1 +v1annealTT_merge3_116k_120k,polymath_en_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a79f92ad61_2026-10-07T16-11-54.727005.json,1791389327.5112891,1 +v1annealTT_merge3_116k_120k,polymath_es_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7ebccfe0c2_2026-10-07T15-45-07.249190.json,1791387724.9242804,1 +v1annealTT_merge3_116k_120k,polymath_es_low,0,lm-eval,vllm,,exact_match,none,0.272,0.03996127157394334,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d2f58d7599_2026-10-07T15-47-26.107589.json,1791387855.674526,1 +v1annealTT_merge3_116k_120k,polymath_es_medium,0,lm-eval,vllm,,exact_match,none,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cbe74613b7_2026-10-07T16-12-11.842949.json,1791389325.9915674,1 +v1annealTT_merge3_116k_120k,polymath_es_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/76b5b34885_2026-10-07T15-49-19.794153.json,1791387973.1400447,1 +v1annealTT_merge3_116k_120k,polymath_fr_high,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/50c2d7a724_2026-10-07T15-37-05.715157.json,1791387229.476079,1 +v1annealTT_merge3_116k_120k,polymath_fr_low,0,lm-eval,vllm,,exact_match,none,0.472,0.0448308649438409,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3dedd3eb97_2026-10-07T15-53-10.108816.json,1791388205.0692146,1 +v1annealTT_merge3_116k_120k,polymath_fr_medium,0,lm-eval,vllm,,exact_match,none,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c22f7db964_2026-10-07T15-49-05.535080.json,1791387962.343574,1 +v1annealTT_merge3_116k_120k,polymath_fr_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/20054cacc8_2026-10-07T15-42-58.703157.json,1791387595.6054463,1 +v1annealTT_merge3_116k_120k,polymath_it_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/33de2e804d_2026-10-07T15-42-55.408075.json,1791387587.0689178,1 +v1annealTT_merge3_116k_120k,polymath_it_low,0,lm-eval,vllm,,exact_match,none,0.392,0.04384135623049351,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/79a583c660_2026-10-07T16-15-41.707613.json,1791389556.2768989,1 +v1annealTT_merge3_116k_120k,polymath_it_medium,0,lm-eval,vllm,,exact_match,none,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/341161e0c2_2026-10-07T15-53-26.146395.json,1791388218.5209837,1 +v1annealTT_merge3_116k_120k,polymath_it_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/38ab3b13c2_2026-10-07T15-53-23.069199.json,1791388218.9411569,1 +v1annealTT_merge3_116k_120k,polymath_pt_high,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7d6c392b4b_2026-10-07T15-49-27.377114.json,1791387977.3843122,1 +v1annealTT_merge3_116k_120k,polymath_pt_low,0,lm-eval,vllm,,exact_match,none,0.304,0.041307657651398745,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2354f34055_2026-10-07T15-53-15.957784.json,1791388210.1150343,1 +v1annealTT_merge3_116k_120k,polymath_pt_medium,0,lm-eval,vllm,,exact_match,none,0.056,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/828775b5be_2026-10-07T15-47-34.246336.json,1791387865.1977973,1 +v1annealTT_merge3_116k_120k,polymath_pt_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a29430b90_2026-10-07T15-45-17.827848.json,1791387730.0106626,1 +v1annealTT_merge3_116k_120k,sib200_als_Latn,0,lm-eval,vllm,,acc,none,0.2549019607843137,0.030587591351604302,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc9d2f63b6_2026-10-07T16-15-29.454757.json,1791389558.7008886,1 +v1annealTT_merge3_116k_120k,sib200_bos_Latn,0,lm-eval,vllm,,acc,none,0.3284313725490196,0.03296245110172227,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/00979ed418_2026-10-07T15-56-57.218509.json,1791388454.9875855,1 +v1annealTT_merge3_116k_120k,sib200_bul_Cyrl,0,lm-eval,vllm,,acc,none,0.5784313725490197,0.03465868196380755,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6c64cd03fd_2026-10-07T15-42-34.664482.json,1791387597.402246,1 +v1annealTT_merge3_116k_120k,sib200_cat_Latn,0,lm-eval,vllm,,acc,none,0.5196078431372549,0.035066125605248695,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f06e908d59_2026-10-07T15-38-35.496537.json,1791387348.405035,1 +v1annealTT_merge3_116k_120k,sib200_ces_Latn,0,lm-eval,vllm,,acc,none,0.49019607843137253,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5dd638dd4f_2026-10-07T15-42-38.435358.json,1791387593.0152805,1 +v1annealTT_merge3_116k_120k,sib200_dan_Latn,0,lm-eval,vllm,,acc,none,0.46568627450980393,0.03501038327635894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d6e6574bfe_2026-10-07T15-50-54.084739.json,1791388096.094707,1 +v1annealTT_merge3_116k_120k,sib200_deu_Latn,0,lm-eval,vllm,,acc,none,0.5588235294117647,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/508a27fe6c_2026-10-07T15-53-03.473223.json,1791388219.0272264,1 +v1annealTT_merge3_116k_120k,sib200_ell_Grek,0,lm-eval,vllm,,acc,none,0.4019607843137255,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/146af6aabb_2026-10-07T15-38-31.227940.json,1791387350.2421863,1 +v1annealTT_merge3_116k_120k,sib200_eng_Latn,0,lm-eval,vllm,,acc,none,0.49019607843137253,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6d32521c35_2026-10-07T15-48-57.934714.json,1791387976.5186958,1 +v1annealTT_merge3_116k_120k,sib200_est_Latn,0,lm-eval,vllm,,acc,none,0.47058823529411764,0.03503235296367989,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5c044f4b54_2026-10-07T15-50-54.015368.json,1791388091.0387163,1 +v1annealTT_merge3_116k_120k,sib200_eus_Latn,0,lm-eval,vllm,,acc,none,0.35294117647058826,0.033540924375915215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ba8389a7b7_2026-10-07T15-38-30.664630.json,1791387348.4763062,1 +v1annealTT_merge3_116k_120k,sib200_fin_Latn,0,lm-eval,vllm,,acc,none,0.46568627450980393,0.03501038327635894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a09fd5a64_2026-10-07T16-11-26.125115.json,1791389324.7448967,1 +v1annealTT_merge3_116k_120k,sib200_fra_Latn,0,lm-eval,vllm,,acc,none,0.5637254901960784,0.03480693138457044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/571b6ad4c0_2026-10-07T15-36-41.030715.json,1791387231.414755,1 +v1annealTT_merge3_116k_120k,sib200_gle_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4d0eb15652_2026-10-07T15-50-49.221448.json,1791388093.563429,1 +v1annealTT_merge3_116k_120k,sib200_glg_Latn,0,lm-eval,vllm,,acc,none,0.4852941176470588,0.035077938347913305,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/64ea8e3bf3_2026-10-07T15-42-33.047797.json,1791387592.9662752,1 +v1annealTT_merge3_116k_120k,sib200_hrv_Latn,0,lm-eval,vllm,,acc,none,0.3088235294117647,0.03242661719827215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/52242b260b_2026-10-07T16-11-15.096897.json,1791389316.0592585,1 +v1annealTT_merge3_116k_120k,sib200_hun_Latn,0,lm-eval,vllm,,acc,none,0.28431372549019607,0.03166009679399808,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c82fd64ec9_2026-10-07T16-19-30.667557.json,1791389805.280848,1 +v1annealTT_merge3_116k_120k,sib200_isl_Latn,0,lm-eval,vllm,,acc,none,0.5098039215686274,0.035086373586305744,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3bbd9a7ed8_2026-10-07T16-19-26.430055.json,1791389804.30404,1 +v1annealTT_merge3_116k_120k,sib200_ita_Latn,0,lm-eval,vllm,,acc,none,0.6029411764705882,0.034341311647191244,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9e7e487f36_2026-10-07T15-51-17.646393.json,1791388096.0071065,1 +v1annealTT_merge3_116k_120k,sib200_kat_Geor,0,lm-eval,vllm,,acc,none,0.31862745098039214,0.032702871814820796,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/741044edb5_2026-10-07T15-36-32.683351.json,1791387227.3275626,1 +v1annealTT_merge3_116k_120k,sib200_lit_Latn,0,lm-eval,vllm,,acc,none,0.5147058823529411,0.035077938347913305,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/84b1c4cbbe_2026-10-07T16-15-26.432895.json,1791389564.8455973,1 +v1annealTT_merge3_116k_120k,sib200_lvs_Latn,0,lm-eval,vllm,,acc,none,0.47058823529411764,0.03503235296367989,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8d2aea80e9_2026-10-07T15-49-03.773296.json,1791387979.709575,1 +v1annealTT_merge3_116k_120k,sib200_mkd_Cyrl,0,lm-eval,vllm,,acc,none,0.46078431372549017,0.03498501649369533,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d1ecc2beee_2026-10-07T15-52-49.307760.json,1791388206.931415,1 +v1annealTT_merge3_116k_120k,sib200_mlt_Latn,0,lm-eval,vllm,,acc,none,0.29411764705882354,0.031980016601150726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6cc5a621d5_2026-10-07T15-42-43.709989.json,1791387602.0244122,1 +v1annealTT_merge3_116k_120k,sib200_nld_Latn,0,lm-eval,vllm,,acc,none,0.4411764705882353,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/76bcf453a8_2026-10-07T15-42-38.227170.json,1791387599.8859046,1 +v1annealTT_merge3_116k_120k,sib200_nob_Latn,0,lm-eval,vllm,,acc,none,0.47549019607843135,0.035050931943487976,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93ef392db1_2026-10-07T15-44-39.202853.json,1791387713.4141366,1 +v1annealTT_merge3_116k_120k,sib200_pol_Latn,0,lm-eval,vllm,,acc,none,0.5245098039215687,0.035050931943487976,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dbfd6b997d_2026-10-07T15-36-20.004598.json,1791387223.6523929,1 +v1annealTT_merge3_116k_120k,sib200_por_Latn,0,lm-eval,vllm,,acc,none,0.5735294117647058,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e52ad26e2_2026-10-07T15-47-06.427985.json,1791387863.2426493,1 +v1annealTT_merge3_116k_120k,sib200_ron_Latn,0,lm-eval,vllm,,acc,none,0.4264705882352941,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7f92fc5c36_2026-10-07T15-42-37.269780.json,1791387594.828739,1 +v1annealTT_merge3_116k_120k,sib200_slk_Latn,0,lm-eval,vllm,,acc,none,0.4362745098039216,0.03480693138457044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/04182caebe_2026-10-07T16-17-21.082191.json,1791389683.7172818,1 +v1annealTT_merge3_116k_120k,sib200_slv_Latn,0,lm-eval,vllm,,acc,none,0.4117647058823529,0.03454236585380609,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f246290ec3_2026-10-07T15-38-37.146153.json,1791387355.330579,1 +v1annealTT_merge3_116k_120k,sib200_spa_Latn,0,lm-eval,vllm,,acc,none,0.5343137254901961,0.03501038327635894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6f5ebcaab8_2026-10-07T15-52-51.404381.json,1791388219.066283,1 +v1annealTT_merge3_116k_120k,sib200_srp_Cyrl,0,lm-eval,vllm,,acc,none,0.4215686274509804,0.03465868196380755,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5560613710_2026-10-07T15-36-37.916615.json,1791387232.6662974,1 +v1annealTT_merge3_116k_120k,sib200_swe_Latn,0,lm-eval,vllm,,acc,none,0.44607843137254904,0.034888454513049706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/63316c39c9_2026-10-07T15-44-48.205129.json,1791387723.3238282,1 +v1annealTT_merge3_116k_120k,sib200_tur_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ca78e5c4b1_2026-10-07T16-11-12.894726.json,1791389308.913099,1 +v1annealTT_merge3_116k_120k,sib200_ukr_Cyrl,0,lm-eval,vllm,,acc,none,0.5735294117647058,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f53769f16f_2026-10-07T15-47-10.181035.json,1791387866.5170665,1 +v1annealTT_merge3_116k_120k,social_iqa,0,lm-eval,vllm,,acc,none,0.5020470829068577,0.011313975730316997,1954,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a4a56eada_2026-10-07T15-38-49.257214.json,1791387346.3043678,1 +v1annealTT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_exact,none,79.45344129554655,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecc66caf71_2026-10-07T16-22-29.111923.json,1791388210.2847707,1 +v1annealTT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_f1,none,85.89603951200044,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecc66caf71_2026-10-07T16-22-29.111923.json,1791388210.2847707,1 +v1annealTT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_exact,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecc66caf71_2026-10-07T16-22-29.111923.json,1791388210.2847707,1 +v1annealTT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_f1,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecc66caf71_2026-10-07T16-22-29.111923.json,1791388210.2847707,1 +v1annealTT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_exact,none,61.04607091720711,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecc66caf71_2026-10-07T16-22-29.111923.json,1791388210.2847707,1 +v1annealTT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_f1,none,62.639259387359196,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecc66caf71_2026-10-07T16-22-29.111923.json,1791388210.2847707,1 +v1annealTT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,exact,none,39.66983913080098,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecc66caf71_2026-10-07T16-22-29.111923.json,1791388210.2847707,1 +v1annealTT_merge3_116k_120k,squadv2,10,lm-eval,vllm,,f1,none,42.88652591822948,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ecc66caf71_2026-10-07T16-22-29.111923.json,1791388210.2847707,1 +v1annealTT_merge3_116k_120k,winogrande,0,lm-eval,vllm,,acc,none,0.7308602999210734,0.01246491195126884,1267,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0bb7b19420_2026-10-07T15-47-01.840068.json,1791387854.303771,1 +v1annealTT_merge3_116k_120k,wsc273,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.021217447349500165,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d12b733eb7_2026-10-07T15-48-53.241644.json,1791387967.9085844,1 +v1annealTT_merge3_116k_120k,xcopa:et,0,lighteval,hf/accelerate,,acc,none,0.636,0.02153917063731769,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/35c8d610e0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-55-30.345614.json,1791388530.4276183,1 +v1annealTT_merge3_116k_120k,xcopa:it,0,lighteval,hf/accelerate,,acc,none,0.708,0.020354375480530085,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ccc16076a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T16-22-09.249014.json,1791390129.3515077,1 +v1annealTT_merge3_116k_120k,xcopa:tr,0,lighteval,hf/accelerate,,acc,none,0.672,0.02101702716517549,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/75874fa82c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1annealTT_merge3_116k_120k/results_2026-10-07T15-55-30.364230.json,1791388530.4512506,1 +v1annealTT_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc,none,0.446,0.01572677116675039,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d03d5395d2_2026-10-07T15-48-54.006772.json,1791387970.3304513,1 +v1annealTT_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc_norm,none,0.433,0.01567663091218125,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d03d5395d2_2026-10-07T15-48-54.006772.json,1791387970.3304513,1 +v1annealTT_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc,none,0.631,0.015266698139154782,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2fc33a1c38_2026-10-07T15-52-56.324301.json,1791388210.092179,1 +v1annealTT_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc_norm,none,0.584,0.015594460144140522,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2fc33a1c38_2026-10-07T15-52-56.324301.json,1791388210.092179,1 +v1annealTT_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc,none,0.463,0.015775927227262426,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/07382a8c85_2026-10-07T15-44-49.637419.json,1791387721.5550132,1 +v1annealTT_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc_norm,none,0.41,0.015560917136921659,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/07382a8c85_2026-10-07T15-44-49.637419.json,1791387721.5550132,1 +v1annealTT_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc,none,0.477,0.015802554246726087,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/df9c24011e_2026-10-07T16-11-26.594804.json,1791389322.9400795,1 +v1annealTT_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc_norm,none,0.412,0.015572363292015074,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/df9c24011e_2026-10-07T16-11-26.594804.json,1791389322.9400795,1 +v1annealTT_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc,none,0.43,0.01566350361015521,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8ab91f7ad0_2026-10-07T16-22-02.458256.json,1791389937.7227507,1 +v1annealTT_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc_norm,none,0.41,0.015560917136921659,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8ab91f7ad0_2026-10-07T16-22-02.458256.json,1791389937.7227507,1 +v1annealTT_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc,none,0.389,0.015424555647308514,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f75ff6dee8_2026-10-07T15-44-55.950329.json,1791387725.741767,1 +v1annealTT_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc_norm,none,0.363,0.01521389044467136,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f75ff6dee8_2026-10-07T15-44-55.950329.json,1791387725.741767,1 +v1annealTT_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.459,0.015766025737882314,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e2bae8629f_2026-10-07T15-53-09.195172.json,1791388215.9149175,1 +v1annealTT_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.432,0.015672320237336324,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e2bae8629f_2026-10-07T15-53-09.195172.json,1791388215.9149175,1 +v1annealTT_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.44,0.015704987954361718,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/91a97edbe0_2026-10-07T15-43-06.855107.json,1791387594.8763556,1 +v1annealTT_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.375,0.015316971293620996,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/91a97edbe0_2026-10-07T15-43-06.855107.json,1791387594.8763556,1 +v1annealTT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@1,all,0.21145833333333333,0.05669292674582661,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/53249584ef_2026-10-08T23-23-01.440453.json,1791500630.342845,1 +v1annealTT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@16,all,0.4601169392111872,0.091423284138234,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/53249584ef_2026-10-08T23-23-01.440453.json,1791500630.342845,1 +v1annealTT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@32,all,0.4666666666666667,0.09264111117062016,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/53249584ef_2026-10-08T23-23-01.440453.json,1791500630.342845,1 +v1annealTT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@4,all,0.36505932517612166,0.07788582517739051,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/53249584ef_2026-10-08T23-23-01.440453.json,1791500630.342845,1 +v1annealTT_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,think_closed,all,0.18958333333333333,0.05612080736373176,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/53249584ef_2026-10-08T23-23-01.440453.json,1791500630.342845,1 +v1annealTT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@1,all,0.2125,0.06776329555251819,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c2dc1ac877_2026-10-08T23-23-28.323052.json,1791500645.3402278,1 +v1annealTT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@16,all,0.3086018809120246,0.08282089806565321,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c2dc1ac877_2026-10-08T23-23-28.323052.json,1791500645.3402278,1 +v1annealTT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@32,all,0.3333333333333333,0.0875376219064817,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c2dc1ac877_2026-10-08T23-23-28.323052.json,1791500645.3402278,1 +v1annealTT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@4,all,0.27194475342973673,0.07927131445564084,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c2dc1ac877_2026-10-08T23-23-28.323052.json,1791500645.3402278,1 +v1annealTT_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,think_closed,all,0.21666666666666667,0.06760630022048178,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c2dc1ac877_2026-10-08T23-23-28.323052.json,1791500645.3402278,1 +v1annealTT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@1,all,0.56484375,0.06184945386103788,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7814f548cf_2026-10-08T23-23-26.704358.json,1791500637.696179,1 +v1annealTT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@16,all,0.9106297721258217,0.03813043444809645,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7814f548cf_2026-10-08T23-23-26.704358.json,1791500637.696179,1 +v1annealTT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@32,all,0.95,0.03489912202260564,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7814f548cf_2026-10-08T23-23-26.704358.json,1791500637.696179,1 +v1annealTT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@4,all,0.7624179644048943,0.05129476136673794,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7814f548cf_2026-10-08T23-23-26.704358.json,1791500637.696179,1 +v1annealTT_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,think_closed,all,0.51015625,0.06818484473754423,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/7814f548cf_2026-10-08T23-23-26.704358.json,1791500637.696179,1 +v1annealTT_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,pass@1,all,0.4444444444444444,0.029092606607853472,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/6f7e21fed4_2026-10-08T23-28-49.784435.json,1791500627.8604352,1 +v1annealTT_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,think_closed,all,0.3446969696969697,0.028756591293005337,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/6f7e21fed4_2026-10-08T23-28-49.784435.json,1791500627.8604352,1 +v1annealTT_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@1,all,0.5373475609756098,0.030969202269188326,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d529759a16_2026-10-08T23-08-56.783064.json,1791500639.140953,1 +v1annealTT_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@16,all,0.8006821536312834,0.030013712132822664,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d529759a16_2026-10-08T23-08-56.783064.json,1791500639.140953,1 +v1annealTT_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@1,all,0.3282766990291262,0.015544900402608678,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ea5172eb17_2026-10-08T23-35-39.176715.json,1791500630.3660343,1 +v1annealTT_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@4,all,0.5553398058252427,0.02191855750756648,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ea5172eb17_2026-10-08T23-35-39.176715.json,1791500630.3660343,1 +v1annealTT_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,think_closed,all,0.43980582524271844,0.01657899225924188,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ea5172eb17_2026-10-08T23-35-39.176715.json,1791500630.3660343,1 +v1annealTT_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@1,all,0.19960861056751467,0.01652194428745977,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2de48b1b92_2026-10-08T23-13-49.057559.json,1791500637.9054265,1 +v1annealTT_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@4,all,0.23953033268101762,0.018838745948339692,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2de48b1b92_2026-10-08T23-13-49.057559.json,1791500637.9054265,1 +v1annealTT_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@1,all,0.7525,0.017126708624151728,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a4867a2eff_2026-10-08T23-26-15.197001.json,1791500639.2322953,1 +v1annealTT_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@4,all,0.844,0.016243636028391108,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a4867a2eff_2026-10-08T23-26-15.197001.json,1791500639.2322953,1 +v1annealTT_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,think_closed,all,0.7695,0.016584317265365994,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a4867a2eff_2026-10-08T23-26-15.197001.json,1791500639.2322953,1 +v1annealTT_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@1,all,0.611125,0.019186778878108615,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8a08a6edc4_2026-10-08T23-11-00.933152.json,1791500634.0023048,1 +v1annealTT_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@16,all,0.7580119080045183,0.018762733583437403,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8a08a6edc4_2026-10-08T23-11-00.933152.json,1791500634.0023048,1 +v1annealTT_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@1,all,0.078,0.02225511901969174,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/cc1ef0c156_2026-10-08T23-15-53.779989.json,1791500630.2166479,1 +v1annealTT_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@4,all,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/cc1ef0c156_2026-10-08T23-15-53.779989.json,1791500630.2166479,1 +v1annealTT_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,think_closed,all,0.104,0.025110080227515368,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/cc1ef0c156_2026-10-08T23-15-53.779989.json,1791500630.2166479,1 +v1annealTT_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@1,all,0.476,0.039698866482558416,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/18873f0d29_2026-10-08T23-08-31.235419.json,1791500629.747303,1 +v1annealTT_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@4,all,0.608,0.04384135623049351,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/18873f0d29_2026-10-08T23-08-31.235419.json,1791500629.747303,1 +v1annealTT_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,think_closed,all,0.982,0.009058946745015794,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/18873f0d29_2026-10-08T23-08-31.235419.json,1791500629.747303,1 +v1annealTT_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@1,all,0.244,0.036639481613462074,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/eb9873f933_2026-10-08T23-16-01.478685.json,1791500634.6491451,1 +v1annealTT_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@4,all,0.288,0.04066543273291013,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/eb9873f933_2026-10-08T23-16-01.478685.json,1791500634.6491451,1 +v1annealTT_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,think_closed,all,0.294,0.03831785568786605,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/eb9873f933_2026-10-08T23-16-01.478685.json,1791500634.6491451,1 +v1annealTT_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/6f63b7f8cd_2026-10-08T23-16-00.639819.json,1791500634.3925989,1 +v1annealTT_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/6f63b7f8cd_2026-10-08T23-16-00.639819.json,1791500634.3925989,1 +v1annealTT_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,think_closed,all,0.012,0.006872103495409022,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/6f63b7f8cd_2026-10-08T23-16-00.639819.json,1791500634.3925989,1 +v1annealTT_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@1,all,0.096,0.022501612845419797,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c20cb7e0ac_2026-10-08T23-16-02.836667.json,1791500631.523183,1 +v1annealTT_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@4,all,0.144,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c20cb7e0ac_2026-10-08T23-16-02.836667.json,1791500631.523183,1 +v1annealTT_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,think_closed,all,0.14,0.028169990896284896,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c20cb7e0ac_2026-10-08T23-16-02.836667.json,1791500631.523183,1 +v1annealTT_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@1,all,0.826,0.027711648884015682,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/41d60574f3_2026-10-08T23-08-25.593641.json,1791500639.170832,1 +v1annealTT_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@4,all,0.912,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/41d60574f3_2026-10-08T23-08-25.593641.json,1791500639.170832,1 +v1annealTT_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,think_closed,all,1.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/41d60574f3_2026-10-08T23-08-25.593641.json,1791500639.170832,1 +v1annealTT_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@1,all,0.264,0.0357301715821562,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/89f52cfe13_2026-10-08T23-15-40.581806.json,1791500626.998643,1 +v1annealTT_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@4,all,0.336,0.04241728193144408,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/89f52cfe13_2026-10-08T23-15-40.581806.json,1791500626.998643,1 +v1annealTT_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,think_closed,all,0.3,0.03636730186804198,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/89f52cfe13_2026-10-08T23-15-40.581806.json,1791500626.998643,1 +v1annealTT_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d156ee298e_2026-10-08T23-16-19.941524.json,1791500648.0136337,1 +v1annealTT_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d156ee298e_2026-10-08T23-16-19.941524.json,1791500648.0136337,1 +v1annealTT_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,think_closed,all,0.024,0.009598386961258882,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d156ee298e_2026-10-08T23-16-19.941524.json,1791500648.0136337,1 +v1annealTT_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@1,all,0.102,0.025095944923690428,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1502d7ba14_2026-10-08T23-15-45.045417.json,1791500631.648885,1 +v1annealTT_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@4,all,0.136,0.030783321835464835,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1502d7ba14_2026-10-08T23-15-45.045417.json,1791500631.648885,1 +v1annealTT_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,think_closed,all,0.124,0.027034028735603195,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1502d7ba14_2026-10-08T23-15-45.045417.json,1791500631.648885,1 +v1annealTT_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@1,all,0.762,0.033342794356260405,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/acfe16f28e_2026-10-08T23-09-11.749223.json,1791500634.8494859,1 +v1annealTT_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@4,all,0.888,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/acfe16f28e_2026-10-08T23-09-11.749223.json,1791500634.8494859,1 +v1annealTT_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,think_closed,all,0.958,0.015485685377564121,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/acfe16f28e_2026-10-08T23-09-11.749223.json,1791500634.8494859,1 +v1annealTT_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@1,all,0.264,0.03958494337416038,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f65e84136c_2026-10-08T23-14-40.921710.json,1791500603.2774858,1 +v1annealTT_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@4,all,0.264,0.03958494337416038,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f65e84136c_2026-10-08T23-14-40.921710.json,1791500603.2774858,1 +v1annealTT_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,think_closed,all,0.32,0.04189079504709142,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f65e84136c_2026-10-08T23-14-40.921710.json,1791500603.2774858,1 +v1annealTT_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.004865944857356966,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2886c995b9_2026-10-08T23-16-06.488486.json,1791500632.6767437,1 +v1annealTT_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@4,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2886c995b9_2026-10-08T23-16-06.488486.json,1791500632.6767437,1 +v1annealTT_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,think_closed,all,0.028,0.00813990568226248,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2886c995b9_2026-10-08T23-16-06.488486.json,1791500632.6767437,1 +v1annealTT_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@1,all,0.104,0.0249489801976599,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/498a7ae5f4_2026-10-08T23-16-00.283594.json,1791500634.8389714,1 +v1annealTT_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@4,all,0.136,0.030783321835464835,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/498a7ae5f4_2026-10-08T23-16-00.283594.json,1791500634.8389714,1 +v1annealTT_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,think_closed,all,0.132,0.026726813888773966,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/498a7ae5f4_2026-10-08T23-16-00.283594.json,1791500634.8389714,1 +v1annealTT_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@1,all,0.84,0.030374012661505398,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a5c2ce27b0_2026-10-08T23-09-22.317141.json,1791500633.7910385,1 +v1annealTT_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@4,all,0.88,0.029182407426835203,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a5c2ce27b0_2026-10-08T23-09-22.317141.json,1791500633.7910385,1 +v1annealTT_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,think_closed,all,0.976,0.011152896340152792,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a5c2ce27b0_2026-10-08T23-09-22.317141.json,1791500633.7910385,1 +v1annealTT_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@1,all,0.256,0.039191835884530846,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2e1f4be944_2026-10-08T23-15-31.835910.json,1791500637.604646,1 +v1annealTT_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@4,all,0.256,0.039191835884530846,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2e1f4be944_2026-10-08T23-15-31.835910.json,1791500637.604646,1 +v1annealTT_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,think_closed,all,0.36,0.043105272486425976,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/2e1f4be944_2026-10-08T23-15-31.835910.json,1791500637.604646,1 +v1annealTT_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.00563399817925698,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/48b75126f2_2026-10-08T23-16-05.039727.json,1791500631.5844283,1 +v1annealTT_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/48b75126f2_2026-10-08T23-16-05.039727.json,1791500631.5844283,1 +v1annealTT_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,think_closed,all,0.036,0.012921599821054817,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/48b75126f2_2026-10-08T23-16-05.039727.json,1791500631.5844283,1 +v1annealTT_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@1,all,0.07,0.019797360527882692,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/0ad01854e7_2026-10-08T23-16-00.654245.json,1791500631.60464,1 +v1annealTT_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@4,all,0.128,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/0ad01854e7_2026-10-08T23-16-00.654245.json,1791500631.60464,1 +v1annealTT_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,think_closed,all,0.072,0.01984130588834411,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/0ad01854e7_2026-10-08T23-16-00.654245.json,1791500631.60464,1 +v1annealTT_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@1,all,0.738,0.033342794356260405,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d92c12776c_2026-10-08T23-08-58.415286.json,1791500624.245595,1 +v1annealTT_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@4,all,0.904,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d92c12776c_2026-10-08T23-08-58.415286.json,1791500624.245595,1 +v1annealTT_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,think_closed,all,0.97,0.012247448713915891,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d92c12776c_2026-10-08T23-08-58.415286.json,1791500624.245595,1 +v1annealTT_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@1,all,0.246,0.034894310470702905,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/cf04e5c2bb_2026-10-08T23-15-45.950247.json,1791500631.491399,1 +v1annealTT_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@4,all,0.328,0.04216098180897563,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/cf04e5c2bb_2026-10-08T23-15-45.950247.json,1791500631.491399,1 +v1annealTT_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,think_closed,all,0.306,0.03722902093797257,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/cf04e5c2bb_2026-10-08T23-15-45.950247.json,1791500631.491399,1 +v1annealTT_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ff141c35ee_2026-10-08T23-15-33.736269.json,1791500603.354317,1 +v1annealTT_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ff141c35ee_2026-10-08T23-15-33.736269.json,1791500603.354317,1 +v1annealTT_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,think_closed,all,0.036,0.012921599821054817,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ff141c35ee_2026-10-08T23-15-33.736269.json,1791500603.354317,1 +v1annealTT_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@1,all,0.098,0.024576411454889015,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ced466ff91_2026-10-08T23-15-37.155623.json,1791500603.3708978,1 +v1annealTT_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@4,all,0.136,0.030783321835464835,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ced466ff91_2026-10-08T23-15-37.155623.json,1791500603.3708978,1 +v1annealTT_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,think_closed,all,0.118,0.02564899545288149,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/ced466ff91_2026-10-08T23-15-37.155623.json,1791500603.3708978,1 +v1annealTT_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@1,all,0.824,0.03419866060384199,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/12d0549a5f_2026-10-08T23-09-15.621507.json,1791500644.018659,1 +v1annealTT_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@4,all,0.824,0.03419866060384199,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/12d0549a5f_2026-10-08T23-09-15.621507.json,1791500644.018659,1 +v1annealTT_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,think_closed,all,0.984,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/12d0549a5f_2026-10-08T23-09-15.621507.json,1791500644.018659,1 +v1annealTT_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@1,all,0.214,0.032341923257592456,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/224e00e1f6_2026-10-08T23-15-39.929983.json,1791500631.0961995,1 +v1annealTT_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@4,all,0.304,0.041307657651398745,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/224e00e1f6_2026-10-08T23-15-39.929983.json,1791500631.0961995,1 +v1annealTT_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,think_closed,all,0.282,0.034428045581773085,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/224e00e1f6_2026-10-08T23-15-39.929983.json,1791500631.0961995,1 +v1annealTT_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@1,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c3a3c40577_2026-10-08T23-16-00.835847.json,1791500633.2677796,1 +v1annealTT_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c3a3c40577_2026-10-08T23-16-00.835847.json,1791500633.2677796,1 +v1annealTT_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,think_closed,all,0.04,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1annealTT_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c3a3c40577_2026-10-08T23-16-00.835847.json,1791500633.2677796,1 diff --git a/results/v1anneal_120k.flag-evals-438.tasks.csv b/results/v1anneal_120k.flag-evals-471.tasks.csv similarity index 95% rename from results/v1anneal_120k.flag-evals-438.tasks.csv rename to results/v1anneal_120k.flag-evals-471.tasks.csv index b5fdab3..5425c98 100644 --- a/results/v1anneal_120k.flag-evals-438.tasks.csv +++ b/results/v1anneal_120k.flag-evals-471.tasks.csv @@ -2021,3 +2021,104 @@ v1anneal_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.453,0.015749255189977683 v1anneal_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.434,0.015680876566375044,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/vllm/2026-10-02-00-04-10/results/ebf22d095e_2026-10-01T22-50-10.828965.json,1790894843.7326796,1 v1anneal_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.427,0.015649789644462186,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/vllm/2026-10-02-00-04-10/results/6dba3b09ec_2026-10-01T22-12-26.648623.json,1790892581.1701639,1 v1anneal_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.404,0.015524980677122437,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/vllm/2026-10-02-00-04-10/results/6dba3b09ec_2026-10-01T22-12-26.648623.json,1790892581.1701639,1 +v1anneal_120k,aime24_cot,0,lm-eval,vllm,,pass@1,all,0.21458333333333332,0.06175441295289825,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/ea712eb56c_2026-10-08T22-30-14.647325.json,1791497486.9317734,1 +v1anneal_120k,aime24_cot,0,lm-eval,vllm,,pass@16,all,0.4071581591607073,0.08732548793283795,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/ea712eb56c_2026-10-08T22-30-14.647325.json,1791497486.9317734,1 +v1anneal_120k,aime24_cot,0,lm-eval,vllm,,pass@32,all,0.43333333333333335,0.09201865544655373,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/ea712eb56c_2026-10-08T22-30-14.647325.json,1791497486.9317734,1 +v1anneal_120k,aime24_cot,0,lm-eval,vllm,,pass@4,all,0.32037356321839083,0.07869601293373228,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/ea712eb56c_2026-10-08T22-30-14.647325.json,1791497486.9317734,1 +v1anneal_120k,aime24_cot,0,lm-eval,vllm,,think_closed,all,0.15833333333333333,0.053583286408874546,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/ea712eb56c_2026-10-08T22-30-14.647325.json,1791497486.9317734,1 +v1anneal_120k,aime25_cot,0,lm-eval,vllm,,pass@1,all,0.20833333333333334,0.06628843857055773,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/332700eb34_2026-10-08T22-30-21.856494.json,1791497482.8491755,1 +v1anneal_120k,aime25_cot,0,lm-eval,vllm,,pass@16,all,0.29831267156572294,0.08463313898709608,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/332700eb34_2026-10-08T22-30-21.856494.json,1791497482.8491755,1 +v1anneal_120k,aime25_cot,0,lm-eval,vllm,,pass@32,all,0.3,0.08509629433967632,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/332700eb34_2026-10-08T22-30-21.856494.json,1791497482.8491755,1 +v1anneal_120k,aime25_cot,0,lm-eval,vllm,,pass@4,all,0.2743177604746014,0.07984657007018388,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/332700eb34_2026-10-08T22-30-21.856494.json,1791497482.8491755,1 +v1anneal_120k,aime25_cot,0,lm-eval,vllm,,think_closed,all,0.1625,0.06086953732954312,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/332700eb34_2026-10-08T22-30-21.856494.json,1791497482.8491755,1 +v1anneal_120k,amc23_cot,0,lm-eval,vllm,,pass@1,all,0.55625,0.06070334285138944,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/bf1b437364_2026-10-08T22-31-06.779016.json,1791497482.8934994,1 +v1anneal_120k,amc23_cot,0,lm-eval,vllm,,pass@16,all,0.8448160595873041,0.05687914531392576,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/bf1b437364_2026-10-08T22-31-06.779016.json,1791497482.8934994,1 +v1anneal_120k,amc23_cot,0,lm-eval,vllm,,pass@32,all,0.85,0.05717718748968655,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/bf1b437364_2026-10-08T22-31-06.779016.json,1791497482.8934994,1 +v1anneal_120k,amc23_cot,0,lm-eval,vllm,,pass@4,all,0.7514557842046719,0.057845098303922864,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/bf1b437364_2026-10-08T22-31-06.779016.json,1791497482.8934994,1 +v1anneal_120k,amc23_cot,0,lm-eval,vllm,,think_closed,all,0.446875,0.06800845712398286,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/bf1b437364_2026-10-08T22-31-06.779016.json,1791497482.8934994,1 +v1anneal_120k,gpqa_diamond_cot,0,lm-eval,vllm,,pass@1,all,0.41414141414141414,0.03102299787214202,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/e3b45eb34f_2026-10-08T22-37-23.753140.json,1791497486.9883144,1 +v1anneal_120k,gpqa_diamond_cot,0,lm-eval,vllm,,think_closed,all,0.3106060606060606,0.029370555417416632,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/e3b45eb34f_2026-10-08T22-37-23.753140.json,1791497486.9883144,1 +v1anneal_120k,humaneval_cont,0,lm-eval,vllm,,pass@1,all,0.5870807926829268,0.030888751203030577,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/7ce4335aa1_2026-10-08T22-16-32.277945.json,1791497486.916782,1 +v1anneal_120k,humaneval_cont,0,lm-eval,vllm,,pass@16,all,0.8272542540380355,0.028662761849628755,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/7ce4335aa1_2026-10-08T22-16-32.277945.json,1791497486.916782,1 +v1anneal_120k,jeebench_cot,0,lm-eval,vllm,,pass@1,all,0.2923543689320388,0.016666078297939868,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/f107b84d10_2026-10-08T22-46-02.714352.json,1791497488.1169333,1 +v1anneal_120k,jeebench_cot,0,lm-eval,vllm,,pass@4,all,0.42330097087378643,0.021793033323114205,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/f107b84d10_2026-10-08T22-46-02.714352.json,1791497488.1169333,1 +v1anneal_120k,jeebench_cot,0,lm-eval,vllm,,think_closed,all,0.3470873786407767,0.017277665942633122,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/f107b84d10_2026-10-08T22-46-02.714352.json,1791497488.1169333,1 +v1anneal_120k,livecodebench_cont,0,lm-eval,vllm,,pass@1,all,0.20058708414872797,0.01664341540810139,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/6510ea53b4_2026-10-08T22-21-15.258662.json,1791497491.8460393,1 +v1anneal_120k,livecodebench_cont,0,lm-eval,vllm,,pass@4,all,0.23765725468269502,0.018792027958681522,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/6510ea53b4_2026-10-08T22-21-15.258662.json,1791497491.8460393,1 +v1anneal_120k,math500_cot,0,lm-eval,vllm,,pass@1,all,0.7575,0.018077363805719258,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/dcd5b6297c_2026-10-08T22-33-36.329773.json,1791497485.8043664,1 +v1anneal_120k,math500_cot,0,lm-eval,vllm,,pass@4,all,0.81,0.01756180041075899,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/dcd5b6297c_2026-10-08T22-33-36.329773.json,1791497485.8043664,1 +v1anneal_120k,math500_cot,0,lm-eval,vllm,,think_closed,all,0.759,0.017971754726121534,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/dcd5b6297c_2026-10-08T22-33-36.329773.json,1791497485.8043664,1 +v1anneal_120k,mbpp_cont,3,lm-eval,vllm,,pass@1,all,0.5815,0.0194897460322294,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/e8067f2898_2026-10-08T22-18-36.893483.json,1791497489.8500311,1 +v1anneal_120k,mbpp_cont,3,lm-eval,vllm,,pass@16,all,0.7369992524860111,0.019286682485606155,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/e8067f2898_2026-10-08T22-18-36.893483.json,1791497489.8500311,1 +v1anneal_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@1,all,0.072,0.020043501078501003,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1d6c6a5303_2026-10-08T22-23-29.832670.json,1791497484.054336,1 +v1anneal_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@4,all,0.12,0.029182407426835203,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1d6c6a5303_2026-10-08T22-23-29.832670.json,1791497484.054336,1 +v1anneal_120k,polymath_de_high_cot,0,lm-eval,vllm,,think_closed,all,0.106,0.023290590651660722,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1d6c6a5303_2026-10-08T22-23-29.832670.json,1791497484.054336,1 +v1anneal_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@1,all,0.792,0.029748407384858164,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/9b28c16261_2026-10-08T22-17-35.333131.json,1791497481.6793363,1 +v1anneal_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@4,all,0.904,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/9b28c16261_2026-10-08T22-17-35.333131.json,1791497481.6793363,1 +v1anneal_120k,polymath_de_low_cot,0,lm-eval,vllm,,think_closed,all,0.954,0.01343562908956101,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/9b28c16261_2026-10-08T22-17-35.333131.json,1791497481.6793363,1 +v1anneal_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@1,all,0.182,0.03267335898093084,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/7ab7f7aa4d_2026-10-08T22-23-22.942309.json,1791497488.569181,1 +v1anneal_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@4,all,0.224,0.03744070581082711,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/7ab7f7aa4d_2026-10-08T22-23-22.942309.json,1791497488.569181,1 +v1anneal_120k,polymath_de_medium_cot,0,lm-eval,vllm,,think_closed,all,0.266,0.0366702833015966,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/7ab7f7aa4d_2026-10-08T22-23-22.942309.json,1791497488.569181,1 +v1anneal_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/7f1ac9f38d_2026-10-08T22-23-34.729804.json,1791497489.8642585,1 +v1anneal_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/7f1ac9f38d_2026-10-08T22-23-34.729804.json,1791497489.8642585,1 +v1anneal_120k,polymath_de_top_cot,0,lm-eval,vllm,,think_closed,all,0.022,0.010631662996188137,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/7f1ac9f38d_2026-10-08T22-23-34.729804.json,1791497489.8642585,1 +v1anneal_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@1,all,0.068,0.019751684289145175,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/2f13377494_2026-10-08T22-23-37.442892.json,1791497489.9087656,1 +v1anneal_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@4,all,0.104,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/2f13377494_2026-10-08T22-23-37.442892.json,1791497489.9087656,1 +v1anneal_120k,polymath_en_high_cot,0,lm-eval,vllm,,think_closed,all,0.118,0.022643093371254617,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/2f13377494_2026-10-08T22-23-37.442892.json,1791497489.9087656,1 +v1anneal_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@1,all,0.88,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/727e379eae_2026-10-08T22-17-25.918676.json,1791497485.4560895,1 +v1anneal_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@4,all,0.944,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/727e379eae_2026-10-08T22-17-25.918676.json,1791497485.4560895,1 +v1anneal_120k,polymath_en_low_cot,0,lm-eval,vllm,,think_closed,all,0.96,0.014591203713417602,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/727e379eae_2026-10-08T22-17-25.918676.json,1791497485.4560895,1 +v1anneal_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@1,all,0.208,0.032717756844001786,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/17d1409e7c_2026-10-08T22-22-52.669048.json,1791497485.6880615,1 +v1anneal_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@4,all,0.272,0.03996127157394334,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/17d1409e7c_2026-10-08T22-22-52.669048.json,1791497485.6880615,1 +v1anneal_120k,polymath_en_medium_cot,0,lm-eval,vllm,,think_closed,all,0.324,0.03692014049531161,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/17d1409e7c_2026-10-08T22-22-52.669048.json,1791497485.6880615,1 +v1anneal_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.00281699908962849,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1d1df00b92_2026-10-08T22-23-23.493421.json,1791497479.1051738,1 +v1anneal_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1d1df00b92_2026-10-08T22-23-23.493421.json,1791497479.1051738,1 +v1anneal_120k,polymath_en_top_cot,0,lm-eval,vllm,,think_closed,all,0.034,0.013423619049537155,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1d1df00b92_2026-10-08T22-23-23.493421.json,1791497479.1051738,1 +v1anneal_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@1,all,0.088,0.023461705242868128,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/e60e1daa0b_2026-10-08T22-23-24.623381.json,1791497482.218604,1 +v1anneal_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@4,all,0.112,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/e60e1daa0b_2026-10-08T22-23-24.623381.json,1791497482.218604,1 +v1anneal_120k,polymath_es_high_cot,0,lm-eval,vllm,,think_closed,all,0.112,0.02594286526319936,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/e60e1daa0b_2026-10-08T22-23-24.623381.json,1791497482.218604,1 +v1anneal_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@1,all,0.854,0.026055771449075376,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/079fcdb149_2026-10-08T22-17-31.548065.json,1791497485.1880786,1 +v1anneal_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@4,all,0.936,0.021979462554702022,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/079fcdb149_2026-10-08T22-17-31.548065.json,1791497485.1880786,1 +v1anneal_120k,polymath_es_low_cot,0,lm-eval,vllm,,think_closed,all,0.936,0.017016121388165228,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/079fcdb149_2026-10-08T22-17-31.548065.json,1791497485.1880786,1 +v1anneal_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@1,all,0.196,0.03169715566765186,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/bc43c2890a_2026-10-08T22-23-39.250797.json,1791497490.5924716,1 +v1anneal_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@4,all,0.288,0.04066543273291013,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/bc43c2890a_2026-10-08T22-23-39.250797.json,1791497490.5924716,1 +v1anneal_120k,polymath_es_medium_cot,0,lm-eval,vllm,,think_closed,all,0.262,0.03612880184258323,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/bc43c2890a_2026-10-08T22-23-39.250797.json,1791497490.5924716,1 +v1anneal_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1b6952e446_2026-10-08T22-23-28.864487.json,1791497486.931287,1 +v1anneal_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1b6952e446_2026-10-08T22-23-28.864487.json,1791497486.931287,1 +v1anneal_120k,polymath_es_top_cot,0,lm-eval,vllm,,think_closed,all,0.04,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1b6952e446_2026-10-08T22-23-28.864487.json,1791497486.931287,1 +v1anneal_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@1,all,0.072,0.020243676830380967,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/ff9b8620d0_2026-10-08T22-23-28.892555.json,1791497485.4075272,1 +v1anneal_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@4,all,0.104,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/ff9b8620d0_2026-10-08T22-23-28.892555.json,1791497485.4075272,1 +v1anneal_120k,polymath_fr_high_cot,0,lm-eval,vllm,,think_closed,all,0.104,0.02221304469987646,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/ff9b8620d0_2026-10-08T22-23-28.892555.json,1791497485.4075272,1 +v1anneal_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@1,all,0.79,0.03328760303970582,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/c2ed2be8ba_2026-10-08T22-17-34.361068.json,1791497479.3795369,1 +v1anneal_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@4,all,0.872,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/c2ed2be8ba_2026-10-08T22-17-34.361068.json,1791497479.3795369,1 +v1anneal_120k,polymath_fr_low_cot,0,lm-eval,vllm,,think_closed,all,0.932,0.01975168428914518,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/c2ed2be8ba_2026-10-08T22-17-34.361068.json,1791497479.3795369,1 +v1anneal_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@1,all,0.18,0.031186225247074876,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/5814e6a5f8_2026-10-08T22-23-17.104358.json,1791497481.0340414,1 +v1anneal_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@4,all,0.256,0.039191835884530846,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/5814e6a5f8_2026-10-08T22-23-17.104358.json,1791497481.0340414,1 +v1anneal_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,think_closed,all,0.282,0.03713271750999944,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/5814e6a5f8_2026-10-08T22-23-17.104358.json,1791497481.0340414,1 +v1anneal_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@1,all,0.012,0.00845099726888547,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/048bc00e83_2026-10-08T22-23-32.232111.json,1791497486.9966002,1 +v1anneal_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/048bc00e83_2026-10-08T22-23-32.232111.json,1791497486.9966002,1 +v1anneal_120k,polymath_fr_top_cot,0,lm-eval,vllm,,think_closed,all,0.046,0.01565350625465477,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/048bc00e83_2026-10-08T22-23-32.232111.json,1791497486.9966002,1 +v1anneal_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@1,all,0.078,0.02075510042250789,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1b0b2e2833_2026-10-08T22-23-48.126322.json,1791497490.3086321,1 +v1anneal_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@4,all,0.128,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1b0b2e2833_2026-10-08T22-23-48.126322.json,1791497490.3086321,1 +v1anneal_120k,polymath_it_high_cot,0,lm-eval,vllm,,think_closed,all,0.102,0.021830727087325568,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/1b0b2e2833_2026-10-08T22-23-48.126322.json,1791497490.3086321,1 +v1anneal_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@1,all,0.84,0.03292219567012406,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/dfdd9749a8_2026-10-08T22-17-03.813461.json,1791497486.9173381,1 +v1anneal_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@4,all,0.84,0.03292219567012406,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/dfdd9749a8_2026-10-08T22-17-03.813461.json,1791497486.9173381,1 +v1anneal_120k,polymath_it_low_cot,0,lm-eval,vllm,,think_closed,all,0.952,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/dfdd9749a8_2026-10-08T22-17-03.813461.json,1791497486.9173381,1 +v1anneal_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@1,all,0.208,0.03120380456538655,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/d87d98be06_2026-10-08T22-23-21.677293.json,1791497486.9647543,1 +v1anneal_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@4,all,0.328,0.04216098180897563,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/d87d98be06_2026-10-08T22-23-21.677293.json,1791497486.9647543,1 +v1anneal_120k,polymath_it_medium_cot,0,lm-eval,vllm,,think_closed,all,0.274,0.033047375572926585,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/d87d98be06_2026-10-08T22-23-21.677293.json,1791497486.9647543,1 +v1anneal_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.006309235422212681,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/fc7b14ae54_2026-10-08T22-23-34.026086.json,1791497488.8450906,1 +v1anneal_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/fc7b14ae54_2026-10-08T22-23-34.026086.json,1791497488.8450906,1 +v1anneal_120k,polymath_it_top_cot,0,lm-eval,vllm,,think_closed,all,0.036,0.010889474053474313,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/fc7b14ae54_2026-10-08T22-23-34.026086.json,1791497488.8450906,1 +v1anneal_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@1,all,0.06,0.01849149761027937,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/8d6497915a_2026-10-08T22-23-23.453896.json,1791497480.7396748,1 +v1anneal_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@4,all,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/8d6497915a_2026-10-08T22-23-23.453896.json,1791497480.7396748,1 +v1anneal_120k,polymath_pt_high_cot,0,lm-eval,vllm,,think_closed,all,0.084,0.020269156609918907,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/8d6497915a_2026-10-08T22-23-23.453896.json,1791497480.7396748,1 +v1anneal_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@1,all,0.832,0.029344450483754985,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/82a813fa1d_2026-10-08T22-17-11.594622.json,1791497487.0231774,1 +v1anneal_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@4,all,0.92,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/82a813fa1d_2026-10-08T22-17-11.594622.json,1791497487.0231774,1 +v1anneal_120k,polymath_pt_low_cot,0,lm-eval,vllm,,think_closed,all,0.93,0.019797360527882696,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/82a813fa1d_2026-10-08T22-17-11.594622.json,1791497487.0231774,1 +v1anneal_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@1,all,0.21,0.03328760303970582,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/068c4521f5_2026-10-08T22-23-19.186014.json,1791497488.5820887,1 +v1anneal_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@4,all,0.288,0.04066543273291013,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/068c4521f5_2026-10-08T22-23-19.186014.json,1791497488.5820887,1 +v1anneal_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,think_closed,all,0.266,0.0360044800079818,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/068c4521f5_2026-10-08T22-23-19.186014.json,1791497488.5820887,1 +v1anneal_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.00281699908962849,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/b2996b8e78_2026-10-08T22-23-37.547800.json,1791497495.2044568,1 +v1anneal_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/b2996b8e78_2026-10-08T22-23-37.547800.json,1791497495.2044568,1 +v1anneal_120k,polymath_pt_top_cot,0,lm-eval,vllm,,think_closed,all,0.024,0.007737633213194812,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_120k/cot/2026-10-09-00-05-19/results/b2996b8e78_2026-10-08T22-23-37.547800.json,1791497495.2044568,1 diff --git a/results/v1anneal_merge3_116k_120k.flag-evals-471.tasks.csv b/results/v1anneal_merge3_116k_120k.flag-evals-471.tasks.csv new file mode 100644 index 0000000..9585c8f --- /dev/null +++ b/results/v1anneal_merge3_116k_120k.flag-evals-471.tasks.csv @@ -0,0 +1,2124 @@ +checkpoint,task,n_shot,harness,backend,is_group,metric,filter,value,stderr,n_samples,results_file,result_time,n_files +v1anneal_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,accuracy_avg,,0.09333333333333334,0.006324555320336759,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4c8a9530a6/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-08-47.453787.json,1791389323.425825,1 +v1anneal_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,solved_avg,,2.8,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4c8a9530a6/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-08-47.453787.json,1791389323.425825,1 +v1anneal_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,accuracy_avg,,0.07333333333333333,0.0042163702135578395,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/37768a9edd/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-24-25.520455.json,1791390260.7965906,1 +v1anneal_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,solved_avg,,2.2,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/37768a9edd/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-24-25.520455.json,1791390260.7965906,1 +v1anneal_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,accuracy_avg,,0.175,0.0,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bc939fc727/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-05-14.005100.json,1791389109.288174,1 +v1anneal_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,solved_avg,,7.0,,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bc939fc727/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-05-14.005100.json,1791389109.288174,1 +v1anneal_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,accuracy_avg,,0.3333333333333333,0.024162794771729498,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/364dfd7c86/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-09-53.255133.json,1791389389.2329757,1 +v1anneal_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,solved_avg,,66.0,,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/364dfd7c86/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-09-53.255133.json,1791389389.2329757,1 +v1anneal_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,python_pass@1,,0.5609756097560976,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cf37d2802c/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T15-39-01.970895.json,1791387538.3303285,1 +v1anneal_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,sh_pass@1,,0.3987341772151899,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cf37d2802c/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T15-39-01.970895.json,1791387538.3303285,1 +v1anneal_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,accuracy_avg,,0.14401294498381875,0.0008036496454019035,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/19c003df9a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-40-15.476621.json,1791391211.5091712,1 +v1anneal_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,solved_avg,,74.16666666666667,,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/19c003df9a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-40-15.476621.json,1791391211.5091712,1 +v1anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_avg,,0.10697977821265492,0.0006523157208088715,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4bfacea62a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-55-26.872278.json,1791392123.33909,1 +v1anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_easy_avg,,0.26556776556776557,0.0018315018315018252,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4bfacea62a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-55-26.872278.json,1791392123.33909,1 +v1anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_hard_avg,,0.008130081300813009,0.0,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4bfacea62a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-55-26.872278.json,1791392123.33909,1 +v1anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_medium_avg,,0.02588996763754045,0.0020467816570669123,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4bfacea62a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-55-26.872278.json,1791392123.33909,1 +v1anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,solved_avg,,54.666666666666664,,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4bfacea62a/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-55-26.872278.json,1791392123.33909,1 +v1anneal_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,accuracy,,0.506,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/30401df36e/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-00-36.037902.json,1791388830.3421805,1 +v1anneal_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,num_solved,,253,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/30401df36e/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v1anneal_merge3_116k_120k/results_2026-10-07T16-00-36.037902.json,1791388830.3421805,1 +v1anneal_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc,none,0.3130434782608696,0.03064426536742555,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b4ca31cbbe_2026-10-07T15-36-42.498690.json,1791387225.3227189,1 +v1anneal_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc_norm,none,0.2826086956521739,0.02975452853823324,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b4ca31cbbe_2026-10-07T15-36-42.498690.json,1791387225.3227189,1 +v1anneal_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc,none,0.5784982935153583,0.014430197069326087,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a3de1974c_2026-10-07T15-55-24.230392.json,1791388337.661129,1 +v1anneal_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc_norm,none,0.6305460750853242,0.014104578366491963,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a3de1974c_2026-10-07T15-55-24.230392.json,1791388337.661129,1 +v1anneal_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc,none,0.5853242320819113,0.014397070564409184,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/910ebd0b9f_2026-10-07T16-12-24.772046.json,1791389324.2896,1 +v1anneal_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc_norm,none,0.6382252559726962,0.014041957945037995,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/910ebd0b9f_2026-10-07T16-12-24.772046.json,1791389324.2896,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc,none,0.5017064846416383,0.014611305705057077,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8988e21a27_2026-10-07T16-20-43.537336.json,1791389803.3828826,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc_norm,none,0.5443686006825939,0.014553749939306847,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8988e21a27_2026-10-07T16-20-43.537336.json,1791389803.3828826,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc,none,0.507679180887372,0.014609667440892515,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b451154be9_2026-10-07T15-41-33.033458.json,1791387472.0353184,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc_norm,none,0.5392491467576792,0.014566303676636534,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b451154be9_2026-10-07T15-41-33.033458.json,1791387472.0353184,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc,none,0.5034129692832765,0.014611050403244159,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ada0da6a8f_2026-10-07T15-43-46.314477.json,1791387594.0738757,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc_norm,none,0.5418088737201365,0.014560220308714553,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ada0da6a8f_2026-10-07T15-43-46.314477.json,1791387594.0738757,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc,none,0.48293515358361777,0.014602878388536585,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/22495720a0_2026-10-07T16-14-39.001972.json,1791389443.048077,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc_norm,none,0.514505119453925,0.014605241081370146,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/22495720a0_2026-10-07T16-14-39.001972.json,1791389443.048077,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc,none,0.49573378839590443,0.014610858923956936,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3e029e7202_2026-10-07T16-00-37.705516.json,1791388586.2580862,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc_norm,none,0.5332764505119454,0.0145789958596058,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3e029e7202_2026-10-07T16-00-37.705516.json,1791388586.2580862,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc,none,0.523037542662116,0.014595873205358168,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a03bd2936_2026-10-07T16-00-16.408300.json,1791388580.4472466,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc_norm,none,0.575938566552901,0.014441889627464344,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4a03bd2936_2026-10-07T16-00-16.408300.json,1791388580.4472466,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc,none,0.4812286689419795,0.014601090150634058,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4d8c4f2859_2026-10-07T16-14-42.387325.json,1791389448.1803036,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc_norm,none,0.5068259385665529,0.014610029151379957,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4d8c4f2859_2026-10-07T16-14-42.387325.json,1791389448.1803036,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc,none,0.4667235494880546,0.0145789958596058,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ca32d6190_2026-10-07T15-58-25.489923.json,1791388463.8143888,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc_norm,none,0.5017064846416383,0.014611305705057077,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ca32d6190_2026-10-07T15-58-25.489923.json,1791388463.8143888,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc,none,0.5341296928327645,0.014577311315231023,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a7af507156_2026-10-07T15-56-15.923617.json,1791388336.211066,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc_norm,none,0.5571672354948806,0.01451557387334892,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a7af507156_2026-10-07T15-56-15.923617.json,1791388336.211066,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc,none,0.4684300341296928,0.014582236460866985,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83c9df09c4_2026-10-07T15-56-09.600354.json,1791388331.920163,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc_norm,none,0.5247440273037542,0.014593487694937702,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83c9df09c4_2026-10-07T15-56-09.600354.json,1791388331.920163,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc,none,0.4735494880546075,0.014590931358120202,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef4c2f662c_2026-10-07T15-37-39.716190.json,1791387228.3113818,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc_norm,none,0.5051194539249146,0.014610624890309135,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef4c2f662c_2026-10-07T15-37-39.716190.json,1791387228.3113818,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc,none,0.5162116040955631,0.014603708567414945,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/47ff538c58_2026-10-07T16-14-24.350889.json,1791389437.0079105,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc_norm,none,0.5546075085324232,0.014523987638344072,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/47ff538c58_2026-10-07T16-14-24.350889.json,1791389437.0079105,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc,none,0.48976109215017066,0.014608326906285005,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/62acaa7880_2026-10-07T15-58-19.322067.json,1791388467.2988293,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc_norm,none,0.5136518771331058,0.01460594342986087,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/62acaa7880_2026-10-07T15-58-19.322067.json,1791388467.2988293,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc,none,0.4735494880546075,0.014590931358120202,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e9f737869_2026-10-07T15-42-03.334487.json,1791387469.2524598,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc_norm,none,0.5196245733788396,0.014600132075947018,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e9f737869_2026-10-07T15-42-03.334487.json,1791387469.2524598,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc,none,0.4803754266211604,0.014600132075947018,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8cd399d61_2026-10-07T15-37-37.673432.json,1791387225.0677006,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc_norm,none,0.5401023890784983,0.01456431885692496,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d8cd399d61_2026-10-07T15-37-37.673432.json,1791387225.0677006,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc,none,0.5093856655290102,0.014608816322065041,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac07f5f290_2026-10-07T15-56-11.250320.json,1791388335.8633368,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc_norm,none,0.5469283276450512,0.014546892052005678,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac07f5f290_2026-10-07T15-56-11.250320.json,1791388335.8633368,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc,none,0.49658703071672355,0.014611050403244159,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/49e3b2fb2a_2026-10-07T16-00-08.380477.json,1791388577.914072,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc_norm,none,0.5366894197952219,0.014572000527756918,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/49e3b2fb2a_2026-10-07T16-00-08.380477.json,1791388577.914072,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc,none,0.5332764505119454,0.0145789958596058,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0ce6084e82_2026-10-07T16-00-12.121035.json,1791388582.5669308,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc_norm,none,0.575938566552901,0.014441889627464344,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0ce6084e82_2026-10-07T16-00-12.121035.json,1791388582.5669308,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc,none,0.5017064846416383,0.014611305705057077,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0feb4d7981_2026-10-07T16-00-15.205724.json,1791388579.3089848,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc_norm,none,0.5324232081911263,0.014580637569995414,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0feb4d7981_2026-10-07T16-00-15.205724.json,1791388579.3089848,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc,none,0.4991467576791809,0.014611369529813302,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09dee3fc63_2026-10-07T15-56-15.876000.json,1791388336.974225,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc_norm,none,0.5486348122866894,0.014542104569955378,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/09dee3fc63_2026-10-07T15-56-15.876000.json,1791388336.974225,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc,none,0.4906143344709898,0.014608816322065041,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d3485cef28_2026-10-07T16-00-14.485806.json,1791388582.4035358,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc_norm,none,0.5298634812286689,0.014585305840007116,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d3485cef28_2026-10-07T16-00-14.485806.json,1791388582.4035358,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc,none,0.49829351535836175,0.014611305705057077,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7afca1ff70_2026-10-07T16-00-11.265693.json,1791388577.6912782,1 +v1anneal_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc_norm,none,0.5546075085324232,0.014523987638344072,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7afca1ff70_2026-10-07T16-00-11.265693.json,1791388577.6912782,1 +v1anneal_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc,none,0.8535353535353535,0.007255132594838457,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2e92403c5f_2026-10-07T16-20-19.503228.json,1791389804.43472,1 +v1anneal_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc_norm,none,0.8598484848484849,0.0071232478681020886,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2e92403c5f_2026-10-07T16-20-19.503228.json,1791389804.43472,1 +v1anneal_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc,none,0.86,0.011572665427400443,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5db0629f6d_2026-10-07T15-41-10.126435.json,1791387478.4344866,1 +v1anneal_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc_norm,none,0.86,0.011572665427400443,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5db0629f6d_2026-10-07T15-41-10.126435.json,1791387478.4344866,1 +v1anneal_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc,none,0.8688888888888889,0.011256983379669072,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83a4c2bb43_2026-10-07T16-19-50.311371.json,1791389804.5306132,1 +v1anneal_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc_norm,none,0.8688888888888889,0.011256983379669072,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83a4c2bb43_2026-10-07T16-19-50.311371.json,1791389804.5306132,1 +v1anneal_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc,none,0.8711111111111111,0.011175441014999328,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b992f71a6d_2026-10-07T15-57-21.670573.json,1791388461.4026175,1 +v1anneal_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc_norm,none,0.8711111111111111,0.011175441014999328,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b992f71a6d_2026-10-07T15-57-21.670573.json,1791388461.4026175,1 +v1anneal_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc,none,0.8777777777777778,0.010924146933565216,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e45ea772b3_2026-10-07T15-42-53.619505.json,1791387595.578136,1 +v1anneal_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc_norm,none,0.8777777777777778,0.010924146933565216,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e45ea772b3_2026-10-07T15-42-53.619505.json,1791387595.578136,1 +v1anneal_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc,none,0.86,0.011572665427400443,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e8d5999d66_2026-10-07T15-42-52.273993.json,1791387588.1415265,1 +v1anneal_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc_norm,none,0.86,0.011572665427400443,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e8d5999d66_2026-10-07T15-42-52.273993.json,1791387588.1415265,1 +v1anneal_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/eb03376ebd_2026-10-07T16-19-48.254617.json,1791389810.608488,1 +v1anneal_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc_norm,none,0.8955555555555555,0.010200209515456861,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/eb03376ebd_2026-10-07T16-19-48.254617.json,1791389810.608488,1 +v1anneal_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc,none,0.8222222222222222,0.012751271589458612,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05b0fb9b2d_2026-10-07T15-55-14.222160.json,1791388336.4066565,1 +v1anneal_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc_norm,none,0.8222222222222222,0.012751271589458612,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05b0fb9b2d_2026-10-07T15-55-14.222160.json,1791388336.4066565,1 +v1anneal_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc,none,0.8477777777777777,0.011981196673569677,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fea09f602c_2026-10-07T15-40-46.835297.json,1791387470.6729963,1 +v1anneal_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc_norm,none,0.8477777777777777,0.011981196673569677,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fea09f602c_2026-10-07T15-40-46.835297.json,1791387470.6729963,1 +v1anneal_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc,none,0.8833333333333333,0.010706705536407178,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e69e78bda0_2026-10-07T15-42-47.083079.json,1791387590.192484,1 +v1anneal_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc_norm,none,0.8833333333333333,0.010706705536407178,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e69e78bda0_2026-10-07T15-42-47.083079.json,1791387590.192484,1 +v1anneal_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc,none,0.8611111111111112,0.011534094424130552,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/310454e3a5_2026-10-07T15-41-14.726480.json,1791387485.23298,1 +v1anneal_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc_norm,none,0.8611111111111112,0.011534094424130552,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/310454e3a5_2026-10-07T15-41-14.726480.json,1791387485.23298,1 +v1anneal_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc,none,0.8477777777777777,0.011981196673569677,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e38efde383_2026-10-07T16-19-44.006153.json,1791389805.2382026,1 +v1anneal_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc_norm,none,0.8477777777777777,0.011981196673569677,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e38efde383_2026-10-07T16-19-44.006153.json,1791389805.2382026,1 +v1anneal_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc,none,0.85,0.01190899866343681,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a5618b8c54_2026-10-07T16-01-12.999456.json,1791388699.1283002,1 +v1anneal_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc_norm,none,0.85,0.01190899866343681,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a5618b8c54_2026-10-07T16-01-12.999456.json,1791388699.1283002,1 +v1anneal_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc,none,0.8444444444444444,0.012087833203630684,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/46655a6802_2026-10-07T15-40-45.638890.json,1791387470.672434,1 +v1anneal_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc_norm,none,0.8444444444444444,0.012087833203630684,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/46655a6802_2026-10-07T15-40-45.638890.json,1791387470.672434,1 +v1anneal_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc,none,0.8622222222222222,0.011495274539524399,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0e060344bf_2026-10-07T15-36-43.754266.json,1791387228.7984974,1 +v1anneal_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc_norm,none,0.8622222222222222,0.011495274539524399,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0e060344bf_2026-10-07T15-36-43.754266.json,1791387228.7984974,1 +v1anneal_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc,none,0.82,0.012813368991665462,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/de365bcf5d_2026-10-07T15-55-03.843564.json,1791388329.8583393,1 +v1anneal_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc_norm,none,0.82,0.012813368991665462,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/de365bcf5d_2026-10-07T15-55-03.843564.json,1791388329.8583393,1 +v1anneal_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc,none,0.85,0.01190899866343681,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8f6490ed1e_2026-10-07T15-36-48.633861.json,1791387223.2359912,1 +v1anneal_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc_norm,none,0.85,0.01190899866343681,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8f6490ed1e_2026-10-07T15-36-48.633861.json,1791387223.2359912,1 +v1anneal_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc,none,0.8566666666666667,0.011686909711653044,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/da50f091ba_2026-10-07T15-40-50.648322.json,1791387471.5671883,1 +v1anneal_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc_norm,none,0.8566666666666667,0.011686909711653044,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/da50f091ba_2026-10-07T15-40-50.648322.json,1791387471.5671883,1 +v1anneal_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc,none,0.84,0.01222699651698952,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2610dbdfc4_2026-10-07T16-13-29.257307.json,1791389435.7877288,1 +v1anneal_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc_norm,none,0.84,0.01222699651698952,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2610dbdfc4_2026-10-07T16-13-29.257307.json,1791389435.7877288,1 +v1anneal_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc,none,0.8655555555555555,0.011377296040197065,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d2e79869b0_2026-10-07T16-13-55.649019.json,1791389455.2090573,1 +v1anneal_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc_norm,none,0.8655555555555555,0.011377296040197065,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d2e79869b0_2026-10-07T16-13-55.649019.json,1791389455.2090573,1 +v1anneal_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc,none,0.8611111111111112,0.011534094424130552,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/030fc1db74_2026-10-07T15-41-00.562947.json,1791387478.0627685,1 +v1anneal_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc_norm,none,0.8611111111111112,0.011534094424130552,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/030fc1db74_2026-10-07T15-41-00.562947.json,1791387478.0627685,1 +v1anneal_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc,none,0.8566666666666667,0.011686909711653044,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5930faad82_2026-10-07T15-40-56.855502.json,1791387478.411305,1 +v1anneal_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc_norm,none,0.8566666666666667,0.011686909711653044,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5930faad82_2026-10-07T15-40-56.855502.json,1791387478.411305,1 +v1anneal_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc,none,0.8533333333333334,0.011799000521176654,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bad55f4463_2026-10-07T15-41-04.026984.json,1791387481.999621,1 +v1anneal_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc_norm,none,0.8533333333333334,0.011799000521176654,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bad55f4463_2026-10-07T15-41-04.026984.json,1791387481.999621,1 +v1anneal_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc,none,0.8655555555555555,0.011377296040197065,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/906673c976_2026-10-07T15-59-19.861400.json,1791388578.2174764,1 +v1anneal_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc_norm,none,0.8655555555555555,0.011377296040197065,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/906673c976_2026-10-07T15-59-19.861400.json,1791388578.2174764,1 +v1anneal_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc,none,0.86,0.011572665427400443,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dce118e0fc_2026-10-07T16-15-41.701818.json,1791389565.0981936,1 +v1anneal_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc_norm,none,0.86,0.011572665427400443,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dce118e0fc_2026-10-07T16-15-41.701818.json,1791389565.0981936,1 +v1anneal_merge3_116k_120k,bigbench_cs_algorithms_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7825757575757576,0.011357814730127208,1320,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ff885d5521_2026-10-07T15-40-51.871396.json,1791387470.8893623,1 +v1anneal_merge3_116k_120k,bigbench_dyck_languages_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.515,0.01581217964181489,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c447ac04e8_2026-10-07T15-36-51.181985.json,1791387226.1751952,1 +v1anneal_merge3_116k_120k,bigbench_language_identification_multiple_choice,10,lm-eval,vllm,,acc,none,0.2016,0.004012150761795167,10000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c478281737_2026-10-07T17-13-32.450229.json,1791389558.1558583,1 +v1anneal_merge3_116k_120k,bigbench_operators_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.8142857142857143,0.026899110619750623,210,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b02238c10e_2026-10-07T15-40-35.088793.json,1791387476.3907049,1 +v1anneal_merge3_116k_120k,bigbench_qa_wikidata_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7154667585256631,0.0031651870798601054,20321,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a100a7bec_2026-10-07T15-59-22.078713.json,1791388464.1043103,1 +v1anneal_merge3_116k_120k,bigbench_repeat_copy_logic_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.5625,0.08909830562090465,32,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4dd5f09788_2026-10-07T15-40-30.873141.json,1791387471.4291458,1 +v1anneal_merge3_116k_120k,boolq,10,lm-eval,vllm,,acc,none,0.8492354740061162,0.006258297244266247,3270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8aab7300f8_2026-10-07T15-43-35.775103.json,1791387473.120731,1 +v1anneal_merge3_116k_120k,commonsense_qa,10,lm-eval,vllm,,acc,none,0.7968877968877969,0.01151825479363406,1221,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/907da0822e_2026-10-07T15-57-33.862634.json,1791388457.1303535,1 +v1anneal_merge3_116k_120k,copa,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/179b949d5b_2026-10-07T16-13-18.759953.json,1791389443.2197406,1 +v1anneal_merge3_116k_120k,coqa,0,lm-eval,vllm,,em,none,0.7003333333333334,0.016730332641127846,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/41669c7241_2026-10-07T15-40-53.270768.json,1791387471.9700725,1 +v1anneal_merge3_116k_120k,coqa,0,lm-eval,vllm,,f1,none,0.8210460224261896,0.012267794470447041,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/41669c7241_2026-10-07T15-40-53.270768.json,1791387471.9700725,1 +v1anneal_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.02963361614738,0.017986076353542848,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/81fc9e7e7f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-29.773405.json,1791389190.651802,1 +v1anneal_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7044088983462545,0.003949726550052883,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/81fc9e7e7f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-29.773405.json,1791389190.651802,1 +v1anneal_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2629896342647284,0.00629718015825616,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/81fc9e7e7f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-29.773405.json,1791389190.651802,1 +v1anneal_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.67255671064511,0.012028636167000532,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/81fc9e7e7f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-29.773405.json,1791389190.651802,1 +v1anneal_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.73213577168946,0.019173040970143385,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2fa23f04a6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-23.768325.json,1791390324.820656,1 +v1anneal_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7082402083590918,0.003874729166992601,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2fa23f04a6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-23.768325.json,1791390324.820656,1 +v1anneal_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2728937123873684,0.006171562284399825,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2fa23f04a6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-23.768325.json,1791390324.820656,1 +v1anneal_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.71435879808455,0.012340338437958679,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2fa23f04a6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-23.768325.json,1791390324.820656,1 +v1anneal_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.03107936007517,0.020411632609929235,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/63fec7cc7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-58.534721.json,1791390419.608626,1 +v1anneal_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6983668605704056,0.003897381793302675,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/63fec7cc7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-58.534721.json,1791390419.608626,1 +v1anneal_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.25355578335207923,0.006002707292382771,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/63fec7cc7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-58.534721.json,1791390419.608626,1 +v1anneal_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.66765257864301,0.012431736193670802,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/63fec7cc7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-58.534721.json,1791390419.608626,1 +v1anneal_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,47.96364767958893,0.018798366436918366,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/faa4af94c4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-08.447789.json,1791389109.589918,1 +v1anneal_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7277656574496841,0.003941695524799367,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/faa4af94c4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-08.447789.json,1791389109.589918,1 +v1anneal_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3105159523165764,0.006779344587879492,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/faa4af94c4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-08.447789.json,1791389109.589918,1 +v1anneal_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.9170420411742,0.012505348627628424,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/faa4af94c4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-08.447789.json,1791389109.589918,1 +v1anneal_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,41.44251621068724,0.018826963758750762,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0ab8a8e3ac/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-05.131031.json,1791389106.274151,1 +v1anneal_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6837190674317232,0.004172077532287162,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0ab8a8e3ac/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-05.131031.json,1791389106.274151,1 +v1anneal_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2474853617999162,0.006185352588346373,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0ab8a8e3ac/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-05.131031.json,1791389106.274151,1 +v1anneal_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.03706719460148,0.013113367781558223,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0ab8a8e3ac/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-05.131031.json,1791389106.274151,1 +v1anneal_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,50.446104914994976,0.019339030187769956,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/48cdeb3cda/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-31.513701.json,1791389132.705332,1 +v1anneal_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7438766194228222,0.003917883882234554,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/48cdeb3cda/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-31.513701.json,1791389132.705332,1 +v1anneal_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3356914686662976,0.006738828173844969,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/48cdeb3cda/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-31.513701.json,1791389132.705332,1 +v1anneal_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,71.66853512534679,0.012940247300587359,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/48cdeb3cda/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-31.513701.json,1791389132.705332,1 +v1anneal_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.26648732467512,0.019397799597217498,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2cc8ab28cf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-44.850898.json,1791390585.751881,1 +v1anneal_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7145947737285757,0.0038955491228249905,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2cc8ab28cf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-44.850898.json,1791390585.751881,1 +v1anneal_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2820788547274406,0.006437790745758214,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2cc8ab28cf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-44.850898.json,1791390585.751881,1 +v1anneal_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.0759050474586,0.012774070081133106,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2cc8ab28cf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-44.850898.json,1791390585.751881,1 +v1anneal_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.02240106683996,0.018271264678973397,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d4b91549de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-20.925566.json,1791390381.972304,1 +v1anneal_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6549355726362505,0.004272285795003181,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d4b91549de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-20.925566.json,1791390381.972304,1 +v1anneal_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21588448399169022,0.0057813266155251,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d4b91549de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-20.925566.json,1791390381.972304,1 +v1anneal_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.17825162241256,0.013282885996116966,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/d4b91549de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-20.925566.json,1791390381.972304,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu,none,33.73845944332252,0.015420048189704175,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/372581afa9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-08-41.198322.json,1791389322.018861,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6231320322305609,0.003868629633367109,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/372581afa9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-08-41.198322.json,1791389322.018861,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17706656066120588,0.004750123970347587,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/372581afa9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-08-41.198322.json,1791389322.018861,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.775710924012095,0.010831405136589771,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/372581afa9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-08-41.198322.json,1791389322.018861,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu,none,31.189742722498952,0.01699017232181681,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b1e0d3956/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-45.166329.json,1791390585.942844,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5898613347974534,0.004518001909421331,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b1e0d3956/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-45.166329.json,1791390585.942844,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1570857368332955,0.004735643091042961,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b1e0d3956/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-45.166329.json,1791390585.942844,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.18089060969653,0.012299571668287261,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b1e0d3956/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-45.166329.json,1791390585.942844,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu,none,40.78523950623598,0.017840087096535878,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a25c103b2a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-24-12.297381.json,1791390253.148999,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6592628448280432,0.0039847668796345655,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a25c103b2a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-24-12.297381.json,1791390253.148999,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.2260366630270705,0.005535202653008913,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a25c103b2a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-24-12.297381.json,1791390253.148999,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,64.68242358588682,0.011775600804875826,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/a25c103b2a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-24-12.297381.json,1791390253.148999,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu,none,44.370118772187624,0.018594585230338738,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/94947f42e4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-49.707175.json,1791389151.188931,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6806853837867518,0.004139195566153833,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/94947f42e4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-49.707175.json,1791389151.188931,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.27393213596327504,0.006124439863432377,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/94947f42e4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-49.707175.json,1791389151.188931,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.72687274739147,0.012735024937823549,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/94947f42e4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-49.707175.json,1791389151.188931,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu,none,31.769754236115023,0.019510525965674437,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7afabb08f5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.790744.json,1791389120.925722,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5824417907635484,0.005002246476135985,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7afabb08f5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.790744.json,1791389120.925722,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16607290408876907,0.0056954555909070215,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7afabb08f5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.790744.json,1791389120.925722,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.21795918354569,0.013938998495929819,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7afabb08f5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.790744.json,1791389120.925722,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu,none,48.02486848542411,0.019355365365345545,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5143c18c0d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-20.719522.json,1791389121.987135,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7089429216138216,0.0042975098882262015,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5143c18c0d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-20.719522.json,1791389121.987135,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3149801085448075,0.006946507026015147,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5143c18c0d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-20.719522.json,1791389121.987135,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.81470979903409,0.012327704668823514,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/5143c18c0d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-20.719522.json,1791389121.987135,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu,none,38.84058235292559,0.020456448710461355,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/28d1317f16/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-06.259185.json,1791389107.195747,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6412627324621408,0.004777663124077581,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/28d1317f16/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-06.259185.json,1791389107.195747,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22648189027164187,0.0063659226317446405,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/28d1317f16/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-06.259185.json,1791389107.195747,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.7809466558231,0.01390874521871068,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/28d1317f16/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-06.259185.json,1791389107.195747,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu,none,26.44001616728281,0.014855860616922862,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fbb3014bd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-56.211769.json,1791389157.415286,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_1,none,0.5348029065727268,0.004344248803994805,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fbb3014bd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-56.211769.json,1791389157.415286,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_4,none,0.12135552997359482,0.003924402618954014,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fbb3014bd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-56.211769.json,1791389157.415286,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,chrf++,rescored,50.99429834737753,0.012401915727463596,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fbb3014bd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-56.211769.json,1791389157.415286,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu,none,26.036723805059676,0.019410006095205646,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1cfa3b3453/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-15.741732.json,1791388997.256159,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5411308520159803,0.005080049637421731,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1cfa3b3453/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-15.741732.json,1791388997.256159,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12278260852877514,0.005173944321678944,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1cfa3b3453/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-15.741732.json,1791388997.256159,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.76969097428219,0.014118511602129801,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1cfa3b3453/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-15.741732.json,1791388997.256159,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu,none,18.321938063372066,0.015420804334464472,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/289fd4b5ad/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-17.138919.json,1791389178.186778,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.4803077932081512,0.004666761228347883,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/289fd4b5ad/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-17.138919.json,1791389178.186778,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.06951844760109852,0.0037192335373072926,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/289fd4b5ad/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-17.138919.json,1791389178.186778,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,51.39993943223343,0.011798471110231485,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/289fd4b5ad/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-17.138919.json,1791389178.186778,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu,none,24.96356035190823,0.019509606080774355,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b9928623d9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-32.667407.json,1791389133.70974,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5166231229690784,0.005064194317086352,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b9928623d9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-32.667407.json,1791389133.70974,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1114351971040787,0.004937973909741201,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b9928623d9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-32.667407.json,1791389133.70974,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.60358008654652,0.013151175200633712,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/b9928623d9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-32.667407.json,1791389133.70974,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu,none,51.09699658327491,0.023069136109399258,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ed896d85f3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-49.678990.json,1791389090.849109,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6999498136921033,0.004916107656199473,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ed896d85f3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-49.678990.json,1791389090.849109,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3635567689341493,0.007896105891815655,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ed896d85f3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-49.678990.json,1791389090.849109,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.7103412182753,0.015515439816308504,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ed896d85f3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-49.678990.json,1791389090.849109,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu,none,32.040740736769834,0.018229344276232698,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9acccce672/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-31-39.619958.json,1791390700.436333,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5832208360951476,0.004564449528906289,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9acccce672/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-31-39.619958.json,1791390700.436333,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16981093521682392,0.005264324581616573,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9acccce672/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-31-39.619958.json,1791390700.436333,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.57124933876513,0.013723526980237492,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9acccce672/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-31-39.619958.json,1791390700.436333,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu,none,37.236948297672974,0.016303413865744337,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7d6ca7971d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-12.647303.json,1791388993.695076,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6371271430379915,0.003784131210910471,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7d6ca7971d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-12.647303.json,1791388993.695076,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20900085730311777,0.005404723647938706,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7d6ca7971d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-12.647303.json,1791388993.695076,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.783032556118336,0.01107830023770095,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7d6ca7971d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-12.647303.json,1791388993.695076,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu,none,30.99369143999962,0.018917459462842488,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/43bbde8ee0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-31-19.089771.json,1791390679.904925,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5744753341757357,0.005076829339719297,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/43bbde8ee0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-31-19.089771.json,1791390679.904925,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.15778020715030958,0.005385541315268736,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/43bbde8ee0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-31-19.089771.json,1791390679.904925,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.11271642832456,0.01382161912511483,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/43bbde8ee0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-31-19.089771.json,1791390679.904925,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu,none,26.052885707343986,0.018316585615715836,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f5678ad5f8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-01.863855.json,1791389043.029823,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5541867219184217,0.004654295719196089,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f5678ad5f8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-01.863855.json,1791389043.029823,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11191190487168107,0.004747826608484772,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f5678ad5f8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-01.863855.json,1791389043.029823,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.46977264963251,0.012961473516042743,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f5678ad5f8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-01.863855.json,1791389043.029823,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu,none,28.423224726192206,0.01808213919793208,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/43ab1109a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-26.059341.json,1791389007.099978,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5382195769942137,0.004871626613539003,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/43ab1109a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-26.059341.json,1791389007.099978,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1394762237995908,0.0052554382435762055,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/43ab1109a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-26.059341.json,1791389007.099978,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,52.89180642196316,0.013579508953862863,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/43ab1109a0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-26.059341.json,1791389007.099978,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu,none,32.6102990391669,0.015152742984034604,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c25a41d5b0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-04.631364.json,1791388985.85714,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5916251994747633,0.003916270466798991,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c25a41d5b0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-04.631364.json,1791388985.85714,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16690595783425013,0.004300093864473607,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c25a41d5b0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-04.631364.json,1791388985.85714,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.71694387922387,0.010501104969735267,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c25a41d5b0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-04.631364.json,1791388985.85714,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu,none,3.0686956576231377,0.006908175474446792,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/eacc753b72/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-37-47.420834.json,1791391067.978205,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_1,none,0.2004840720463111,0.004018006610576081,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/eacc753b72/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-37-47.420834.json,1791391067.978205,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_4,none,0.004682687803345797,0.0008656124493965691,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/eacc753b72/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-37-47.420834.json,1791391067.978205,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,chrf++,rescored,25.450351873872556,0.008942362526808575,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/eacc753b72/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-37-47.420834.json,1791391067.978205,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu,none,25.970838764730043,0.018760818181381887,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b9ccc19ca/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-08-52.692205.json,1791389333.658034,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5402626987073249,0.004996153657388269,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b9ccc19ca/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-08-52.692205.json,1791389333.658034,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11941408651027385,0.004950749914519573,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b9ccc19ca/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-08-52.692205.json,1791389333.658034,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.083431206647504,0.013154771958531337,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b9ccc19ca/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-08-52.692205.json,1791389333.658034,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu,none,31.008981300454913,0.02025407273057058,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e11b3ee23b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-27-45.289838.json,1791390466.449008,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5864009430780753,0.005245546400669547,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e11b3ee23b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-27-45.289838.json,1791390466.449008,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16626996217784284,0.0061417604478550695,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e11b3ee23b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-27-45.289838.json,1791390466.449008,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.19201308314636,0.014716476551461362,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e11b3ee23b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-27-45.289838.json,1791390466.449008,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu,none,35.93683482314357,0.016707676381800547,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8727addc7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-24.884422.json,1791389005.99907,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6280707770020443,0.003833783963533038,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8727addc7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-24.884422.json,1791389005.99907,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.18852750098088064,0.004995514723588649,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8727addc7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-24.884422.json,1791389005.99907,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,61.656786586242475,0.011233651233757606,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/8727addc7e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-24.884422.json,1791389005.99907,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu,none,38.76184793741921,0.02002410940876534,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/11fa9172ae/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-28-30.559131.json,1791390511.36281,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6390498241828403,0.004688927257297404,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/11fa9172ae/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-28-30.559131.json,1791390511.36281,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22807430665295503,0.00652864605320238,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/11fa9172ae/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-28-30.559131.json,1791390511.36281,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.82628927526308,0.014082025307280683,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/11fa9172ae/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-28-30.559131.json,1791390511.36281,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu,none,27.884947515214037,0.016520620064038292,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c5ae805477/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-31.586338.json,1791389012.82277,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5739066803311902,0.004433507481683931,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c5ae805477/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-31.586338.json,1791389012.82277,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12824495116842752,0.0045113837795492375,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c5ae805477/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-31.586338.json,1791389012.82277,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.70578333068572,0.011901801217631139,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c5ae805477/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-31.586338.json,1791389012.82277,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu,none,34.14566931394714,0.015786971874308418,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e4d69e2d1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-04.770139.json,1791390366.002146,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6123499734303952,0.0039020367187661844,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e4d69e2d1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-04.770139.json,1791390366.002146,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16962130704651027,0.004623029363476574,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e4d69e2d1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-04.770139.json,1791390366.002146,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.704157706395065,0.01089749883238273,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/e4d69e2d1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-04.770139.json,1791390366.002146,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu,none,22.655966048233164,0.016233726620685163,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17f4a17796/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-21.639451.json,1791389003.083057,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5019659311813928,0.004560455216153337,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17f4a17796/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-21.639451.json,1791389003.083057,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.09716354455199726,0.0041117807272084556,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17f4a17796/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-21.639451.json,1791389003.083057,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,49.38412072866657,0.012017107674086728,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/17f4a17796/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-21.639451.json,1791389003.083057,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu,none,49.987774309436624,0.020239253731116298,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/aca9f34390/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.831682.json,1791389120.7838,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7242741764097488,0.004471779151226566,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/aca9f34390/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.831682.json,1791389120.7838,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.33815307221394064,0.007549865017371464,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/aca9f34390/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.831682.json,1791389120.7838,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.71100175262502,0.01337753078585348,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/aca9f34390/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.831682.json,1791389120.7838,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu,none,40.51094786008996,0.018534135197059997,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ec06e9703c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-44.559029.json,1791389025.588632,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6458261412924028,0.004574738471624776,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ec06e9703c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-44.559029.json,1791389025.588632,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.25098258274364854,0.00631159252161547,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ec06e9703c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-44.559029.json,1791389025.588632,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.67063251212157,0.012711885288250744,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ec06e9703c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-44.559029.json,1791389025.588632,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu,none,33.94839687911429,0.02085788053791502,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6c0f6f6cbd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-57.723518.json,1791390358.596928,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5985883351855843,0.005247376293229725,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6c0f6f6cbd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-57.723518.json,1791390358.596928,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1883456416633852,0.006239159013913725,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6c0f6f6cbd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-57.723518.json,1791390358.596928,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.02055537471008,0.014665439177908517,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/6c0f6f6cbd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-57.723518.json,1791390358.596928,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu,none,30.754562650013547,0.018883548918732684,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b6e696c83/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-16.920108.json,1791389118.003567,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5783491162246026,0.005020266213606699,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b6e696c83/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-16.920108.json,1791389118.003567,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16099462127499178,0.005508160614729903,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b6e696c83/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-16.920108.json,1791389118.003567,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.73964464962059,0.013898632995322634,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7b6e696c83/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-16.920108.json,1791389118.003567,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu,none,28.926517410538647,0.013180068474212518,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/84b4caf029/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-30-16.505241.json,1791390617.335598,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.575975962414132,0.0035284915641286183,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/84b4caf029/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-30-16.505241.json,1791390617.335598,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.13667011213753036,0.003727450188530114,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/84b4caf029/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-30-16.505241.json,1791390617.335598,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.31552428713837,0.009934686438364032,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/84b4caf029/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-30-16.505241.json,1791390617.335598,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu,none,34.938815943016294,0.01832795875425528,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f886d56b84/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-22.275577.json,1791389183.30365,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6171248187527982,0.004724320450115192,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f886d56b84/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-22.275577.json,1791389183.30365,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.19130422081616993,0.005477392137628401,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f886d56b84/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-22.275577.json,1791389183.30365,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,59.42793014600603,0.01316056003574978,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f886d56b84/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-22.275577.json,1791389183.30365,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu,none,45.12535697967006,0.02000013899373243,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/289ae1bef7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-03.240569.json,1791389044.101791,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6849919691592138,0.004462192024566039,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/289ae1bef7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-03.240569.json,1791389044.101791,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2804289280900419,0.00684968792983396,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/289ae1bef7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-03.240569.json,1791389044.101791,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.04721390888099,0.013215529214845182,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/289ae1bef7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-03.240569.json,1791389044.101791,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu,none,25.588427999709833,0.018381066490890018,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cb55aff3b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-33.629496.json,1791389015.016275,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5419512515483154,0.004886932185125541,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cb55aff3b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-33.629496.json,1791389015.016275,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11860347481227954,0.005047615083013223,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cb55aff3b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-33.629496.json,1791389015.016275,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.119368141095535,0.01304411112034321,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cb55aff3b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-33.629496.json,1791389015.016275,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu,none,29.74397254118219,0.018424017617828147,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cf2adf13eb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-07-57.851087.json,1791389278.921784,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.5543790506298204,0.005010315037782397,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cf2adf13eb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-07-57.851087.json,1791389278.921784,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.1458263241896308,0.00505270088858848,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cf2adf13eb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-07-57.851087.json,1791389278.921784,1 +v1anneal_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,55.13167137400885,0.013375737240353193,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/cf2adf13eb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-07-57.851087.json,1791389278.921784,1 +v1anneal_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.110187120886444,0.01909667155808701,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c17f36aaeb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-44.349710.json,1791390405.168463,1 +v1anneal_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6672135493977364,0.0043214471934085435,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c17f36aaeb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-44.349710.json,1791390405.168463,1 +v1anneal_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2239095589585314,0.006140338679487568,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c17f36aaeb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-44.349710.json,1791390405.168463,1 +v1anneal_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.98289110729333,0.013205646480175416,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c17f36aaeb/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-44.349710.json,1791390405.168463,1 +v1anneal_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,32.22107144820802,0.017887580588871566,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ced5500d96/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-23.564335.json,1791389004.765287,1 +v1anneal_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6102531020959243,0.004449575767232706,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ced5500d96/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-23.564335.json,1791389004.765287,1 +v1anneal_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16769981230344752,0.00537534743322573,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ced5500d96/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-23.564335.json,1791389004.765287,1 +v1anneal_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.31980663149794,0.013246212859253014,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/ced5500d96/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-23.564335.json,1791389004.765287,1 +v1anneal_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.5851793913569,0.01762668685393973,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bbc46bee20/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-32.569849.json,1791389133.989854,1 +v1anneal_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6496247801802171,0.004225907162527166,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bbc46bee20/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-32.569849.json,1791389133.989854,1 +v1anneal_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20152013219955356,0.005753834735673095,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bbc46bee20/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-32.569849.json,1791389133.989854,1 +v1anneal_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.15680300285066,0.012743610959527476,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/bbc46bee20/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-32.569849.json,1791389133.989854,1 +v1anneal_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.11469933104484,0.02065539240632219,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0de8fb33aa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-11.789350.json,1791388992.932506,1 +v1anneal_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7171777189489472,0.004294610723151613,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0de8fb33aa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-11.789350.json,1791388992.932506,1 +v1anneal_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3012183181420311,0.006962736981699316,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0de8fb33aa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-11.789350.json,1791388992.932506,1 +v1anneal_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.46674534376169,0.013934218216108457,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0de8fb33aa/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-11.789350.json,1791388992.932506,1 +v1anneal_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.44406715355509,0.020567292088806963,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/686c2f182a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-01.049333.json,1791389161.868293,1 +v1anneal_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6918537036270878,0.00442976795554792,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/686c2f182a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-01.049333.json,1791389161.868293,1 +v1anneal_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2740625215257291,0.006795905042964555,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/686c2f182a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-01.049333.json,1791389161.868293,1 +v1anneal_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.12823940118597,0.014265410590002421,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/686c2f182a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-06-01.049333.json,1791389161.868293,1 +v1anneal_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.33262970413238,0.01817812568150201,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f21a7c4fc3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-16.238976.json,1791389117.250466,1 +v1anneal_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6996803228737064,0.003990145024046579,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f21a7c4fc3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-16.238976.json,1791389117.250466,1 +v1anneal_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2682910942826278,0.006409427630857079,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f21a7c4fc3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-16.238976.json,1791389117.250466,1 +v1anneal_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.17369914338003,0.012008806027080945,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f21a7c4fc3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-16.238976.json,1791389117.250466,1 +v1anneal_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.82222263740381,0.018767609030778856,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f9a723b482/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-20.054714.json,1791390381.119031,1 +v1anneal_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.665138427458972,0.004239071676965425,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f9a723b482/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-20.054714.json,1791390381.119031,1 +v1anneal_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21898737327937864,0.005858027956227254,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f9a723b482/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-20.054714.json,1791390381.119031,1 +v1anneal_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.151219764668966,0.01321157708163074,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f9a723b482/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-20.054714.json,1791390381.119031,1 +v1anneal_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.42889021878703,0.018282337105336235,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4f8ab1dbf7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-58.973314.json,1791390359.89543,1 +v1anneal_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6527524225502782,0.004195986765581108,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4f8ab1dbf7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-58.973314.json,1791390359.89543,1 +v1anneal_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20752952192519572,0.005693363447213387,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4f8ab1dbf7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-58.973314.json,1791390359.89543,1 +v1anneal_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.7600206889658,0.012708985890264599,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/4f8ab1dbf7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-58.973314.json,1791390359.89543,1 +v1anneal_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.13251261181121,0.019990522657221666,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/88da5b08dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-08.542030.json,1791389109.410905,1 +v1anneal_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6509338720334015,0.004364018053478025,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/88da5b08dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-08.542030.json,1791389109.410905,1 +v1anneal_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21750718737471444,0.006216122848473721,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/88da5b08dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-08.542030.json,1791389109.410905,1 +v1anneal_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.17401996548435,0.013405915395031684,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/88da5b08dc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-08.542030.json,1791389109.410905,1 +v1anneal_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,35.2061792907686,0.016607461361112685,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f2be65187e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-48.998878.json,1791390350.450557,1 +v1anneal_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6461051950652531,0.0038100164125775505,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f2be65187e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-48.998878.json,1791390350.450557,1 +v1anneal_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.19010509671977022,0.005141365003387845,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f2be65187e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-48.998878.json,1791390350.450557,1 +v1anneal_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.7988985903249,0.011626849702575277,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f2be65187e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-25-48.998878.json,1791390350.450557,1 +v1anneal_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,18.523288193855688,0.015390115229461841,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2f10c791ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-40-52.231523.json,1791391252.878511,1 +v1anneal_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.4809285956065008,0.004580775089856945,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2f10c791ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-40-52.231523.json,1791391252.878511,1 +v1anneal_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.07015976254196098,0.00322334460367786,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2f10c791ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-40-52.231523.json,1791391252.878511,1 +v1anneal_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,44.441883802332036,0.013569667718502413,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/2f10c791ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-40-52.231523.json,1791391252.878511,1 +v1anneal_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,35.71943662012535,0.019100166372145063,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/69dae8ea1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-01.143290.json,1791388982.249898,1 +v1anneal_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6321782730488946,0.004533607590692874,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/69dae8ea1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-01.143290.json,1791388982.249898,1 +v1anneal_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.19501417574410854,0.005755308372806409,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/69dae8ea1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-01.143290.json,1791388982.249898,1 +v1anneal_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.57713046457512,0.013778426965391598,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/69dae8ea1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-01.143290.json,1791388982.249898,1 +v1anneal_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.51522996369339,0.02054574061639044,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f90a8d3049/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-30-05.888117.json,1791390606.734582,1 +v1anneal_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6592189273245923,0.0044163803801663005,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f90a8d3049/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-30-05.888117.json,1791390606.734582,1 +v1anneal_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.220450211665121,0.006164602361027997,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f90a8d3049/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-30-05.888117.json,1791390606.734582,1 +v1anneal_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.725803097004096,0.014040284755331957,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/f90a8d3049/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-30-05.888117.json,1791390606.734582,1 +v1anneal_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.68139192338638,0.020523315715051952,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b400af5e5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-50.235655.json,1791389031.08318,1 +v1anneal_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7090240970165992,0.003873565504048828,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b400af5e5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-50.235655.json,1791389031.08318,1 +v1anneal_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2747542707212614,0.006159093862268399,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b400af5e5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-50.235655.json,1791389031.08318,1 +v1anneal_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.59434854627247,0.012774661214486777,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9b400af5e5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-50.235655.json,1791389031.08318,1 +v1anneal_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,56.29053590700381,0.020963809257674947,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1b01848a10/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-25.406883.json,1791389066.301426,1 +v1anneal_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7754091141642828,0.004010429264608308,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1b01848a10/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-25.406883.json,1791389066.301426,1 +v1anneal_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.40543333892631306,0.007490915459906387,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1b01848a10/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-25.406883.json,1791389066.301426,1 +v1anneal_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,75.95387166674794,0.012943597522819685,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/1b01848a10/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-25.406883.json,1791389066.301426,1 +v1anneal_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,32.58470285011752,0.018664694318488502,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c2f94aa711/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-22.162301.json,1791389003.161072,1 +v1anneal_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6097282465569424,0.004236197216533857,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c2f94aa711/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-22.162301.json,1791389003.161072,1 +v1anneal_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16379884064433006,0.0051434223565935576,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c2f94aa711/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-22.162301.json,1791389003.161072,1 +v1anneal_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.293604045689804,0.013256586306334594,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c2f94aa711/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-22.162301.json,1791389003.161072,1 +v1anneal_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.568779856442745,0.017967123283416587,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/77f4763fd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-56.659978.json,1791389097.706982,1 +v1anneal_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7005454252135341,0.003923425434498664,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/77f4763fd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-56.659978.json,1791389097.706982,1 +v1anneal_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.27893847916400377,0.006068148479090927,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/77f4763fd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-56.659978.json,1791389097.706982,1 +v1anneal_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.44060017171287,0.012149850076619582,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/77f4763fd6/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-56.659978.json,1791389097.706982,1 +v1anneal_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,32.05943069182893,0.01800359209222615,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/24e2a8e1d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-36.640938.json,1791390577.447833,1 +v1anneal_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6100531499583162,0.004325305204143982,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/24e2a8e1d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-36.640938.json,1791390577.447833,1 +v1anneal_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16256636576819541,0.0051313068809846745,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/24e2a8e1d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-36.640938.json,1791390577.447833,1 +v1anneal_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.45533788601717,0.012926112519347213,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/24e2a8e1d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-29-36.640938.json,1791390577.447833,1 +v1anneal_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,50.70574785341194,0.019372402697277996,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9836251f0c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-53.072188.json,1791389154.175487,1 +v1anneal_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7467214534409788,0.004022779644463699,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9836251f0c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-53.072188.json,1791389154.175487,1 +v1anneal_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3419601022751103,0.0070865971213341546,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9836251f0c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-53.072188.json,1791389154.175487,1 +v1anneal_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.0027388252251,0.01275722526637736,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/9836251f0c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-53.072188.json,1791389154.175487,1 +v1anneal_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.318308336178596,0.018769594617468008,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c25a3afe83/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-06.742878.json,1791389107.62183,1 +v1anneal_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7129530745775254,0.0040521751386692105,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c25a3afe83/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-06.742878.json,1791389107.62183,1 +v1anneal_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2841504663720328,0.006496891805697028,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c25a3afe83/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-06.742878.json,1791389107.62183,1 +v1anneal_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.54603065294458,0.012554206388096779,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/c25a3afe83/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-06.742878.json,1791389107.62183,1 +v1anneal_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.95655789497957,0.019991624502882048,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fbf6fdf0b3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-23.040922.json,1791389124.145947,1 +v1anneal_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6777466972115221,0.004337788652109571,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fbf6fdf0b3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-23.040922.json,1791389124.145947,1 +v1anneal_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.24116033328768857,0.006330173151063652,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fbf6fdf0b3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-23.040922.json,1791389124.145947,1 +v1anneal_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,64.85630373008046,0.013386487276584468,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/fbf6fdf0b3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-23.040922.json,1791389124.145947,1 +v1anneal_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.4220342515284,0.01874591882473861,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/db12bf9654/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-10.077968.json,1791388991.647424,1 +v1anneal_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6562127062245179,0.0041446066271827045,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/db12bf9654/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-10.077968.json,1791388991.647424,1 +v1anneal_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20755057701775445,0.005759860360246539,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/db12bf9654/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-10.077968.json,1791388991.647424,1 +v1anneal_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.84744980486426,0.0130485330468472,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/db12bf9654/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-10.077968.json,1791388991.647424,1 +v1anneal_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,32.90795619157624,0.016970834766190008,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/98d10ab26c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-09.505851.json,1791389050.632081,1 +v1anneal_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6247802944943335,0.004103760630948738,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/98d10ab26c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-09.505851.json,1791389050.632081,1 +v1anneal_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1736785607870944,0.005087744320570789,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/98d10ab26c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-09.505851.json,1791389050.632081,1 +v1anneal_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.724812883685466,0.012272031053458692,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/98d10ab26c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-04-09.505851.json,1791389050.632081,1 +v1anneal_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.04382047666264,0.02088574744492365,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0f29d8f4b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-56.790732.json,1791389037.788522,1 +v1anneal_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7120275881230317,0.004088053587315468,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0f29d8f4b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-56.790732.json,1791389037.788522,1 +v1anneal_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28442548382723637,0.006524620836819579,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0f29d8f4b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-56.790732.json,1791389037.788522,1 +v1anneal_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.02061273850015,0.012843414809658227,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0f29d8f4b1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-03-56.790732.json,1791389037.788522,1 +v1anneal_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,49.99643663299296,0.018714738566831167,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0eefd39682/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-01.990682.json,1791390362.969836,1 +v1anneal_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7378441699808164,0.0037969642664255933,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0eefd39682/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-01.990682.json,1791390362.969836,1 +v1anneal_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3261662165300661,0.0066099715512144405,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0eefd39682/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-01.990682.json,1791390362.969836,1 +v1anneal_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.57059258546057,0.01256225305061909,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/0eefd39682/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-26-01.990682.json,1791390362.969836,1 +v1anneal_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.18116444884674,0.01832754836044785,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/47cf702de7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-15.526564.json,1791389116.687769,1 +v1anneal_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6644138461482053,0.004403012653040205,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/47cf702de7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-15.526564.json,1791389116.687769,1 +v1anneal_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22710744340006583,0.00633456923647285,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/47cf702de7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-15.526564.json,1791389116.687769,1 +v1anneal_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.78272109934879,0.013018272751805613,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/47cf702de7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-15.526564.json,1791389116.687769,1 +v1anneal_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,41.98637866662875,0.01893995189364943,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/dc21eee4b9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.450466.json,1791389120.624432,1 +v1anneal_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6849310258062478,0.004241279142067997,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/dc21eee4b9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.450466.json,1791389120.624432,1 +v1anneal_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2514347867261817,0.006299079395827775,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/dc21eee4b9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.450466.json,1791389120.624432,1 +v1anneal_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.2941265686546,0.013372793081744784,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/dc21eee4b9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-05-19.450466.json,1791389120.624432,1 +v1anneal_merge3_116k_120k,global_mgsm_ca,5,lm-eval,vllm,,exact_match,flexible-extract,0.312,0.02936106757521982,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/485e63a586_2026-10-07T16-13-27.034936.json,1791389443.0145643,1 +v1anneal_merge3_116k_120k,global_mgsm_cs,5,lm-eval,vllm,,exact_match,flexible-extract,0.3,0.029040893477575862,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3141017975_2026-10-07T16-01-12.575281.json,1791388702.8213024,1 +v1anneal_merge3_116k_120k,global_mgsm_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.284,0.028576958730437398,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6ba2c6df54_2026-10-07T15-55-06.379499.json,1791388332.7202818,1 +v1anneal_merge3_116k_120k,global_mgsm_el,5,lm-eval,vllm,,exact_match,flexible-extract,0.316,0.029462657598578704,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/abb56a03cf_2026-10-07T15-42-42.165997.json,1791387596.549294,1 +v1anneal_merge3_116k_120k,global_mgsm_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.336,0.029933259094191512,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a532c7641a_2026-10-07T15-54-58.943293.json,1791388336.2265174,1 +v1anneal_merge3_116k_120k,global_mgsm_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.308,0.029256928606501864,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4455616029_2026-10-07T15-55-04.546250.json,1791388338.489525,1 +v1anneal_merge3_116k_120k,global_mgsm_eu,5,lm-eval,vllm,,exact_match,flexible-extract,0.26,0.0277973157526443,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6c16964694_2026-10-07T15-59-14.884465.json,1791388575.5168703,1 +v1anneal_merge3_116k_120k,global_mgsm_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.288,0.028697004587398205,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b52bf20f19_2026-10-07T15-40-31.897273.json,1791387466.1727884,1 +v1anneal_merge3_116k_120k,global_mgsm_gl,5,lm-eval,vllm,,exact_match,flexible-extract,0.3,0.029040893477575862,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4f2abfd88e_2026-10-07T15-42-39.020364.json,1791387591.4674075,1 +v1anneal_merge3_116k_120k,global_mgsm_hu,5,lm-eval,vllm,,exact_match,flexible-extract,0.272,0.028200088296310016,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1241c4d127_2026-10-07T16-21-38.615755.json,1791389928.3428204,1 +v1anneal_merge3_116k_120k,global_mgsm_sr,5,lm-eval,vllm,,exact_match,flexible-extract,0.3,0.029040893477575856,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c0afb17aa8_2026-10-07T15-40-38.998870.json,1791387471.5740116,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs,5,lm-eval,vllm,yes,acc,none,0.6311066799601196,0.0038881832055694173,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_abstract_algebra,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_anatomy,5,lm-eval,vllm,,acc,none,0.4888888888888889,0.043182754919779784,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_astronomy,5,lm-eval,vllm,,acc,none,0.7302631578947368,0.036117805602848975,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6641509433962264,0.029067220146644885,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_college_biology,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.038520846960085356,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_college_mathematics,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_college_medicine,5,lm-eval,vllm,,acc,none,0.6069364161849711,0.0372424959581773,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_computer_security,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6723404255319149,0.030683020843230994,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6413793103448275,0.03996629574876715,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6455026455026455,0.024636830602842035,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_formal_logic,5,lm-eval,vllm,,acc,none,0.5158730158730159,0.044698818540726104,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_global_facts,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_biology,5,lm-eval,vllm,,acc,none,0.7806451612903226,0.023540799358723274,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5812807881773399,0.03471192860518467,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7454545454545455,0.03401506715249038,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_geography,5,lm-eval,vllm,,acc,none,0.7828282828282829,0.02937661648494561,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.676923076923077,0.023710888501970607,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.43703703703703706,0.030242862397654047,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7478991596638656,0.02820554503327774,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8128440366972477,0.016722684526200172,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6157407407407407,0.03317354514310747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7843137254901961,0.028867431449849337,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8059071729957806,0.025744902532290916,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_human_aging,5,lm-eval,vllm,,acc,none,0.7085201793721974,0.03050028317654591,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_human_sexuality,5,lm-eval,vllm,,acc,none,0.7480916030534351,0.03807387116306089,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_humanities,5,lm-eval,vllm,yes,acc,none,0.5636556854410202,0.006809482030116111,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_jurisprudence,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.04019107472557348,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6687116564417178,0.03697983910025588,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_machine_learning,5,lm-eval,vllm,,acc,none,0.45535714285714285,0.04726835553719097,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_management,5,lm-eval,vllm,,acc,none,0.7184466019417476,0.044532548363264673,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_marketing,5,lm-eval,vllm,,acc,none,0.8376068376068376,0.024161618127987734,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_miscellaneous,5,lm-eval,vllm,,acc,none,0.7241379310344828,0.01598281477469557,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_moral_disputes,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.02378620325550823,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_moral_scenarios,5,lm-eval,vllm,,acc,none,0.358659217877095,0.016040454426164447,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_nutrition,5,lm-eval,vllm,,acc,none,0.7026143790849673,0.026173908506718597,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_other,5,lm-eval,vllm,yes,acc,none,0.6562600579336981,0.008291527917657507,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_philosophy,5,lm-eval,vllm,,acc,none,0.6881028938906752,0.026311858071854183,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_prehistory,5,lm-eval,vllm,,acc,none,0.7006172839506173,0.025483115601195486,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_professional_accounting,5,lm-eval,vllm,,acc,none,0.43617021276595747,0.02958345203628408,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_professional_law,5,lm-eval,vllm,,acc,none,0.439374185136897,0.012676014778580338,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_professional_medicine,5,lm-eval,vllm,,acc,none,0.6544117647058824,0.0288881931039887,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_professional_psychology,5,lm-eval,vllm,,acc,none,0.6830065359477124,0.01882421951270626,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_public_relations,5,lm-eval,vllm,,acc,none,0.6363636363636364,0.04607582090719978,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_security_studies,5,lm-eval,vllm,,acc,none,0.746938775510204,0.027833023871399704,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7435814104647384,0.007765203813612723,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_stem,5,lm-eval,vllm,yes,acc,none,0.59720900729464,0.008510025405932348,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_cs_world_religions,5,lm-eval,vllm,,acc,none,0.7602339181286549,0.03274485211946959,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b34696c5fa_2026-10-07T15-43-24.721274.json,1791387468.3000653,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de,5,lm-eval,vllm,yes,acc,none,0.6303233157669847,0.0038953295128770758,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_abstract_algebra,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_anatomy,5,lm-eval,vllm,,acc,none,0.5481481481481482,0.04299268905480864,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_astronomy,5,lm-eval,vllm,,acc,none,0.743421052631579,0.035541803680256875,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_business_ethics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.660377358490566,0.029146904747798335,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_college_biology,5,lm-eval,vllm,,acc,none,0.7430555555555556,0.03653946969442102,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_college_computer_science,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_college_mathematics,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_college_medicine,5,lm-eval,vllm,,acc,none,0.6358381502890174,0.03669072477416912,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_college_physics,5,lm-eval,vllm,,acc,none,0.4117647058823529,0.048971049527263624,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6978723404255319,0.03001755447188058,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_econometrics,5,lm-eval,vllm,,acc,none,0.5964912280701754,0.04615186962583705,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6344827586206897,0.04013124195424389,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6216931216931217,0.024976954053155278,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_formal_logic,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.044444444444444446,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_global_facts,5,lm-eval,vllm,,acc,none,0.35,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_biology,5,lm-eval,vllm,,acc,none,0.7935483870967742,0.023025899617188667,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6157635467980296,0.03422398565657553,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7393939393939394,0.03427743175816526,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_geography,5,lm-eval,vllm,,acc,none,0.7828282828282829,0.02937661648494561,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8808290155440415,0.02338193534812143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.676923076923077,0.023710888501970607,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4222222222222222,0.030114442019668074,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7394957983193278,0.028510251512341933,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_physics,5,lm-eval,vllm,,acc,none,0.44370860927152317,0.04056527902281736,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8091743119266055,0.01684767640009113,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5740740740740741,0.03372343271653058,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.03132179803083291,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7848101265822784,0.026750826994676173,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_human_aging,5,lm-eval,vllm,,acc,none,0.6636771300448431,0.031708824268455046,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_human_sexuality,5,lm-eval,vllm,,acc,none,0.7404580152671756,0.03844876139785267,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_humanities,5,lm-eval,vllm,yes,acc,none,0.5566418703506908,0.006873838308538523,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_international_law,5,lm-eval,vllm,,acc,none,0.768595041322314,0.03849856098794088,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_jurisprudence,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.04330043749650743,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6809815950920245,0.03661997551073836,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_machine_learning,5,lm-eval,vllm,,acc,none,0.4642857142857143,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_management,5,lm-eval,vllm,,acc,none,0.7281553398058253,0.04405268024140923,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_marketing,5,lm-eval,vllm,,acc,none,0.8632478632478633,0.022509033937077844,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_medical_genetics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_miscellaneous,5,lm-eval,vllm,,acc,none,0.7509578544061303,0.015464676163396064,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_moral_disputes,5,lm-eval,vllm,,acc,none,0.6271676300578035,0.026033890613576312,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3340782122905028,0.015774911422381653,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_nutrition,5,lm-eval,vllm,,acc,none,0.7124183006535948,0.025917806117147137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_other,5,lm-eval,vllm,yes,acc,none,0.6639845510138397,0.00823283620719348,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_philosophy,5,lm-eval,vllm,,acc,none,0.7106109324758842,0.02575586592263286,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_prehistory,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.02492200116888636,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_professional_accounting,5,lm-eval,vllm,,acc,none,0.46808510638297873,0.02976667507587383,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_professional_law,5,lm-eval,vllm,,acc,none,0.4621903520208605,0.012733671880342502,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_professional_medicine,5,lm-eval,vllm,,acc,none,0.6102941176470589,0.029624663581159675,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_professional_psychology,5,lm-eval,vllm,,acc,none,0.6601307189542484,0.019162418588623484,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_public_relations,5,lm-eval,vllm,,acc,none,0.6454545454545455,0.04582004841505413,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_security_studies,5,lm-eval,vllm,,acc,none,0.6816326530612244,0.029822533793982028,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7357816054598635,0.007836530163639511,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_stem,5,lm-eval,vllm,yes,acc,none,0.60418648905804,0.008452220636203475,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_virology,5,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_de_world_religions,5,lm-eval,vllm,,acc,none,0.7660818713450293,0.032467217651178305,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4408b2ab0_2026-10-07T15-57-59.876121.json,1791388333.0852814,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el,5,lm-eval,vllm,yes,acc,none,0.6041874376869392,0.003990906073291083,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_abstract_algebra,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_anatomy,5,lm-eval,vllm,,acc,none,0.5185185185185185,0.043163785995113245,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_astronomy,5,lm-eval,vllm,,acc,none,0.7105263157894737,0.03690677986137281,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_business_ethics,5,lm-eval,vllm,,acc,none,0.55,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6113207547169811,0.03000048544867597,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_college_biology,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.04155319955593143,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_college_chemistry,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_college_medicine,5,lm-eval,vllm,,acc,none,0.6069364161849711,0.0372424959581773,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_computer_security,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6638297872340425,0.03088161852067694,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_econometrics,5,lm-eval,vllm,,acc,none,0.4649122807017544,0.04692008381368906,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_electrical_engineering,5,lm-eval,vllm,,acc,none,0.5655172413793104,0.041307408795554966,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.025010749116137626,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_formal_logic,5,lm-eval,vllm,,acc,none,0.5238095238095238,0.04467062628403266,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_global_facts,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_biology,5,lm-eval,vllm,,acc,none,0.7516129032258064,0.024580028921481045,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5566502463054187,0.03495334582162933,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_european_history,5,lm-eval,vllm,,acc,none,0.696969696969697,0.035886248000917116,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_geography,5,lm-eval,vllm,,acc,none,0.7373737373737373,0.031353050095330834,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8290155440414507,0.02717121368316455,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6743589743589744,0.023759665767412275,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7310924369747899,0.028801392193631228,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_physics,5,lm-eval,vllm,,acc,none,0.4768211920529801,0.04078093859163086,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_psychology,5,lm-eval,vllm,,acc,none,0.7541284403669725,0.018461940968708502,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6018518518518519,0.033384734032073975,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7303921568627451,0.031145570659486796,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7848101265822784,0.026750826994676173,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_human_aging,5,lm-eval,vllm,,acc,none,0.6636771300448431,0.031708824268455046,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_human_sexuality,5,lm-eval,vllm,,acc,none,0.6641221374045801,0.04142313771996665,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_humanities,5,lm-eval,vllm,yes,acc,none,0.553028692879915,0.006964981572097689,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_international_law,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.03520893951097652,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6625766871165644,0.03714908409935573,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_machine_learning,5,lm-eval,vllm,,acc,none,0.39285714285714285,0.04635550135609972,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_management,5,lm-eval,vllm,,acc,none,0.7184466019417476,0.044532548363264673,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_marketing,5,lm-eval,vllm,,acc,none,0.8205128205128205,0.025140935950335442,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_medical_genetics,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_miscellaneous,5,lm-eval,vllm,,acc,none,0.6590038314176245,0.01695178138322336,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_moral_disputes,5,lm-eval,vllm,,acc,none,0.661849710982659,0.025469770149400144,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_moral_scenarios,5,lm-eval,vllm,,acc,none,0.38994413407821227,0.016312376629213008,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_nutrition,5,lm-eval,vllm,,acc,none,0.6633986928104575,0.0270579746244944,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_other,5,lm-eval,vllm,yes,acc,none,0.6099130994528484,0.008544328513690903,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_philosophy,5,lm-eval,vllm,,acc,none,0.6816720257234726,0.026457225067810987,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_prehistory,5,lm-eval,vllm,,acc,none,0.6203703703703703,0.027002521034516468,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_professional_accounting,5,lm-eval,vllm,,acc,none,0.40425531914893614,0.029275532159704753,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_professional_law,5,lm-eval,vllm,,acc,none,0.4485006518904824,0.012702317490559806,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_professional_medicine,5,lm-eval,vllm,,acc,none,0.5698529411764706,0.030074971917302858,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_professional_psychology,5,lm-eval,vllm,,acc,none,0.6094771241830066,0.01973700899809455,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_security_studies,5,lm-eval,vllm,,acc,none,0.7510204081632653,0.027682979522960276,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7049073773155671,0.008099717473519834,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_sociology,5,lm-eval,vllm,,acc,none,0.8258706467661692,0.026814951200421624,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_stem,5,lm-eval,vllm,yes,acc,none,0.576593720266413,0.008632173751314769,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_virology,5,lm-eval,vllm,,acc,none,0.4578313253012048,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_el_world_religions,5,lm-eval,vllm,,acc,none,0.695906432748538,0.03528211258245229,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5b92009a16_2026-10-07T16-19-13.089486.json,1791389563.863391,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en,5,lm-eval,vllm,yes,acc,none,0.6890756302521008,0.0037346840299741137,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_anatomy,5,lm-eval,vllm,,acc,none,0.5333333333333333,0.043097329010363616,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_business_ethics,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_college_computer_science,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_college_mathematics,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_college_medicine,5,lm-eval,vllm,,acc,none,0.653179190751445,0.03629146670159661,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7787234042553192,0.027136349602424097,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_econometrics,5,lm-eval,vllm,,acc,none,0.5789473684210527,0.04644602091222323,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6620689655172414,0.03941707632064884,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6878306878306878,0.02386520683697267,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_formal_logic,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.043603148600774626,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_biology,5,lm-eval,vllm,,acc,none,0.8548387096774194,0.020039563628053293,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6403940886699507,0.0337645824650957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_european_history,5,lm-eval,vllm,,acc,none,0.793939393939394,0.03158415324047706,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_geography,5,lm-eval,vllm,,acc,none,0.8232323232323232,0.027178752639044908,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9326424870466321,0.01808839383907894,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7692307692307693,0.0213620277252227,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5444444444444444,0.03036486250482447,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8151260504201681,0.025215992877954195,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_physics,5,lm-eval,vllm,,acc,none,0.5231788079470199,0.04078093859163086,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8715596330275229,0.014344977542914248,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6574074074074074,0.0323658525260216,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8284313725490197,0.026460569561240675,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8396624472573839,0.02388438092596563,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_human_sexuality,5,lm-eval,vllm,,acc,none,0.732824427480916,0.03880848301082397,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_humanities,5,lm-eval,vllm,yes,acc,none,0.6323060573857598,0.006703907502880221,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_jurisprudence,5,lm-eval,vllm,,acc,none,0.8055555555555556,0.038260763248848646,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7730061349693251,0.03291099578615763,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_machine_learning,5,lm-eval,vllm,,acc,none,0.5357142857142857,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_management,5,lm-eval,vllm,,acc,none,0.8058252427184466,0.03916667762822582,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_marketing,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.02058849131609242,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_miscellaneous,5,lm-eval,vllm,,acc,none,0.8071519795657727,0.014108533515757481,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_moral_disputes,5,lm-eval,vllm,,acc,none,0.7543352601156069,0.023176298203992085,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4692737430167598,0.016690896161944517,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_nutrition,5,lm-eval,vllm,,acc,none,0.7156862745098039,0.025829163272757385,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_other,5,lm-eval,vllm,yes,acc,none,0.7058255551979401,0.007886707263789441,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_philosophy,5,lm-eval,vllm,,acc,none,0.7684887459807074,0.023956532766639154,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_prehistory,5,lm-eval,vllm,,acc,none,0.7592592592592593,0.0237885835516586,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_professional_accounting,5,lm-eval,vllm,,acc,none,0.48936170212765956,0.029820747191422466,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_professional_law,5,lm-eval,vllm,,acc,none,0.5097783572359843,0.012767793787729296,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_professional_medicine,5,lm-eval,vllm,,acc,none,0.6654411764705882,0.028661996202335335,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_professional_psychology,5,lm-eval,vllm,,acc,none,0.7303921568627451,0.017952449196987838,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_security_studies,5,lm-eval,vllm,,acc,none,0.746938775510204,0.027833023871399704,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7920051998700033,0.007190446861746068,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_sociology,5,lm-eval,vllm,,acc,none,0.8507462686567164,0.02519692987482706,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_stem,5,lm-eval,vllm,yes,acc,none,0.6568347605455123,0.008181038839790274,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_virology,5,lm-eval,vllm,,acc,none,0.5301204819277109,0.03885425420866771,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_en_world_religions,5,lm-eval,vllm,,acc,none,0.7953216374269005,0.03094445977853322,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a13f0267cc_2026-10-07T15-45-25.633258.json,1791387595.3345304,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es,5,lm-eval,vllm,yes,acc,none,0.6412191995442245,0.0038636503246977797,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_abstract_algebra,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_anatomy,5,lm-eval,vllm,,acc,none,0.4666666666666667,0.043097329010363616,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_astronomy,5,lm-eval,vllm,,acc,none,0.7631578947368421,0.03459777606810534,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6339622641509434,0.02964781353936531,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_college_biology,5,lm-eval,vllm,,acc,none,0.7361111111111112,0.036856510958975304,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_college_medicine,5,lm-eval,vllm,,acc,none,0.6011560693641619,0.03733626655383514,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_computer_security,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6936170212765957,0.03013590647851759,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_econometrics,5,lm-eval,vllm,,acc,none,0.6140350877192983,0.04579639422070431,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6620689655172414,0.03941707632064884,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.656084656084656,0.0244644266255964,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_global_facts,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_biology,5,lm-eval,vllm,,acc,none,0.8193548387096774,0.021886178567172513,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7757575757575758,0.03256866661681102,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_geography,5,lm-eval,vllm,,acc,none,0.797979797979798,0.02860620428922983,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8601036269430051,0.025033870583015143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7025641025641025,0.02317740813146596,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45185185185185184,0.030343862998512657,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7815126050420168,0.026841514322958934,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_physics,5,lm-eval,vllm,,acc,none,0.45695364238410596,0.0406732517424744,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8201834862385321,0.016465345467391534,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_statistics,5,lm-eval,vllm,,acc,none,0.625,0.033016908987210894,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7892156862745098,0.028626547912437423,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8185654008438819,0.025085961144579647,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_human_aging,5,lm-eval,vllm,,acc,none,0.695067264573991,0.03089861088247754,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_humanities,5,lm-eval,vllm,yes,acc,none,0.5706695005313497,0.006788357944525281,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_international_law,5,lm-eval,vllm,,acc,none,0.7520661157024794,0.039418975265163046,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_machine_learning,5,lm-eval,vllm,,acc,none,0.48214285714285715,0.047427623612430116,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_marketing,5,lm-eval,vllm,,acc,none,0.8162393162393162,0.0253721396717229,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_miscellaneous,5,lm-eval,vllm,,acc,none,0.7432950191570882,0.01562048026306451,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_moral_disputes,5,lm-eval,vllm,,acc,none,0.708092485549133,0.02447699407624737,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_moral_scenarios,5,lm-eval,vllm,,acc,none,0.32849162011173183,0.01570793539849636,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_nutrition,5,lm-eval,vllm,,acc,none,0.6830065359477124,0.02664327847450882,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_other,5,lm-eval,vllm,yes,acc,none,0.6581911812037335,0.008298869652852094,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_philosophy,5,lm-eval,vllm,,acc,none,0.7041800643086816,0.025922371788818833,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_prehistory,5,lm-eval,vllm,,acc,none,0.7191358024691358,0.025006469755799246,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_professional_accounting,5,lm-eval,vllm,,acc,none,0.48226950354609927,0.02980873964223769,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_professional_law,5,lm-eval,vllm,,acc,none,0.46740547588005216,0.012743072942653333,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_professional_medicine,5,lm-eval,vllm,,acc,none,0.6176470588235294,0.029520095697687675,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_professional_psychology,5,lm-eval,vllm,,acc,none,0.6764705882352942,0.018926082916083393,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_security_studies,5,lm-eval,vllm,,acc,none,0.7510204081632653,0.027682979522960276,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7530061748456288,0.007695774035654434,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_sociology,5,lm-eval,vllm,,acc,none,0.7960199004975125,0.02849317624532607,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_stem,5,lm-eval,vllm,yes,acc,none,0.6206787186806216,0.008377880416838691,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_virology,5,lm-eval,vllm,,acc,none,0.4759036144578313,0.03887971849597268,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_es_world_religions,5,lm-eval,vllm,,acc,none,0.7602339181286549,0.03274485211946959,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0133b9e317_2026-10-07T16-00-19.482306.json,1791388463.6339076,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr,5,lm-eval,vllm,yes,acc,none,0.6406494801310355,0.003871996888020571,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_anatomy,5,lm-eval,vllm,,acc,none,0.5185185185185185,0.043163785995113245,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_astronomy,5,lm-eval,vllm,,acc,none,0.75,0.03523807393012047,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_business_ethics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.690566037735849,0.028450154794118682,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_college_biology,5,lm-eval,vllm,,acc,none,0.7291666666666666,0.03716177437566019,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_college_computer_science,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_college_medicine,5,lm-eval,vllm,,acc,none,0.6473988439306358,0.03643037168958545,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_computer_security,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6723404255319149,0.030683020843230994,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_econometrics,5,lm-eval,vllm,,acc,none,0.5701754385964912,0.04657047260594963,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6,0.040824829046386304,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6322751322751323,0.02483383982556237,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_global_facts,5,lm-eval,vllm,,acc,none,0.34,0.04760952285695233,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8,0.02275520495954297,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.034139638059062394,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7636363636363637,0.03317505930009174,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7676767676767676,0.030088629490217438,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8601036269430051,0.025033870583015143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6512820512820513,0.024162780284017697,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.42962962962962964,0.030182099804387304,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7521008403361344,0.028047967224176896,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_physics,5,lm-eval,vllm,,acc,none,0.48344370860927155,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8385321100917431,0.01577623925616323,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.03293377139415187,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7794117647058824,0.029102254389674065,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8059071729957806,0.025744902532290916,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_human_aging,5,lm-eval,vllm,,acc,none,0.6816143497757847,0.03126580522513711,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7480916030534351,0.03807387116306089,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_humanities,5,lm-eval,vllm,yes,acc,none,0.5827842720510096,0.006786299678265574,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_international_law,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.03520893951097652,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.03957835471980979,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7300613496932515,0.034878251684978955,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_machine_learning,5,lm-eval,vllm,,acc,none,0.44642857142857145,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_marketing,5,lm-eval,vllm,,acc,none,0.8162393162393162,0.0253721396717229,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_medical_genetics,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7509578544061303,0.015464676163396064,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.37318435754189944,0.016175692013381957,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_nutrition,5,lm-eval,vllm,,acc,none,0.7156862745098039,0.025829163272757385,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_other,5,lm-eval,vllm,yes,acc,none,0.6700997747022852,0.00820422311163089,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_philosophy,5,lm-eval,vllm,,acc,none,0.7041800643086816,0.025922371788818833,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_prehistory,5,lm-eval,vllm,,acc,none,0.7345679012345679,0.024569223600460856,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_professional_accounting,5,lm-eval,vllm,,acc,none,0.46808510638297873,0.02976667507587383,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_professional_law,5,lm-eval,vllm,,acc,none,0.46479791395045633,0.012738547371304124,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6580882352941176,0.02881472242225415,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6454248366013072,0.01935336054755364,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_public_relations,5,lm-eval,vllm,,acc,none,0.6363636363636364,0.04607582090719978,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_security_studies,5,lm-eval,vllm,,acc,none,0.7591836734693878,0.027372942201788125,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7367565810854728,0.007796824510679484,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_sociology,5,lm-eval,vllm,,acc,none,0.7860696517412935,0.028996909693328965,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_stem,5,lm-eval,vllm,yes,acc,none,0.60418648905804,0.008459302747232769,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_fr_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2a1da4f4be_2026-10-07T16-04-25.261941.json,1791388703.342505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it,5,lm-eval,vllm,yes,acc,none,0.6351659307790913,0.003876102243463299,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_abstract_algebra,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_anatomy,5,lm-eval,vllm,,acc,none,0.5259259259259259,0.043135316967505756,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_astronomy,5,lm-eval,vllm,,acc,none,0.7763157894736842,0.033911609343436046,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6452830188679245,0.029445175328199655,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_college_biology,5,lm-eval,vllm,,acc,none,0.7361111111111112,0.036856510958975304,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_college_mathematics,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_college_medicine,5,lm-eval,vllm,,acc,none,0.6069364161849711,0.0372424959581773,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_college_physics,5,lm-eval,vllm,,acc,none,0.5784313725490197,0.049135952012745024,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_computer_security,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7063829787234043,0.02977164271249127,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6216931216931217,0.024976954053155278,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_formal_logic,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04426266681379905,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_biology,5,lm-eval,vllm,,acc,none,0.8225806451612904,0.021732540689329255,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6403940886699507,0.0337645824650957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7393939393939394,0.03427743175816526,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_geography,5,lm-eval,vllm,,acc,none,0.7626262626262627,0.030313710538198924,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8497409326424871,0.025787723180723855,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.676923076923077,0.023710888501970607,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4666666666666667,0.03041771696171749,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.027553614467863825,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_physics,5,lm-eval,vllm,,acc,none,0.48344370860927155,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8422018348623853,0.015630022970092496,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6018518518518519,0.033384734032073975,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7990196078431373,0.02812597226565433,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7890295358649789,0.0265583725026619,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_human_aging,5,lm-eval,vllm,,acc,none,0.6860986547085202,0.031146796482972486,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_human_sexuality,5,lm-eval,vllm,,acc,none,0.7404580152671756,0.03844876139785267,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_humanities,5,lm-eval,vllm,yes,acc,none,0.5587672688629118,0.006800294610581424,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7239263803680982,0.035123852837050454,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_machine_learning,5,lm-eval,vllm,,acc,none,0.4732142857142857,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_management,5,lm-eval,vllm,,acc,none,0.7281553398058253,0.04405268024140923,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_marketing,5,lm-eval,vllm,,acc,none,0.7905982905982906,0.026655699653922706,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_miscellaneous,5,lm-eval,vllm,,acc,none,0.7394636015325671,0.015696008563807068,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_moral_disputes,5,lm-eval,vllm,,acc,none,0.7138728323699421,0.02433214677913417,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_moral_scenarios,5,lm-eval,vllm,,acc,none,0.33519553072625696,0.015788007190185846,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_nutrition,5,lm-eval,vllm,,acc,none,0.6895424836601307,0.026493033225145922,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_other,5,lm-eval,vllm,yes,acc,none,0.6559382040553589,0.008334572343752445,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_philosophy,5,lm-eval,vllm,,acc,none,0.6977491961414791,0.026082700695399676,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_prehistory,5,lm-eval,vllm,,acc,none,0.6820987654320988,0.02591006352824088,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_professional_accounting,5,lm-eval,vllm,,acc,none,0.46808510638297873,0.02976667507587383,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_professional_law,5,lm-eval,vllm,,acc,none,0.438722294654498,0.012673969883493123,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_professional_medicine,5,lm-eval,vllm,,acc,none,0.6323529411764706,0.029289413409403213,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_professional_psychology,5,lm-eval,vllm,,acc,none,0.6617647058823529,0.019139943748487008,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_public_relations,5,lm-eval,vllm,,acc,none,0.6454545454545455,0.04582004841505413,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_security_studies,5,lm-eval,vllm,,acc,none,0.7346938775510204,0.028263889943784655,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7445563860903477,0.00773193509462047,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_stem,5,lm-eval,vllm,yes,acc,none,0.6219473517285126,0.008404261573770595,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_it_world_religions,5,lm-eval,vllm,,acc,none,0.7602339181286549,0.03274485211946959,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b59795413_2026-10-07T16-00-02.634271.json,1791388457.7043102,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt,5,lm-eval,vllm,yes,acc,none,0.5994160376014813,0.0039467102318436,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_anatomy,5,lm-eval,vllm,,acc,none,0.5407407407407407,0.04304979692464244,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_astronomy,5,lm-eval,vllm,,acc,none,0.7302631578947368,0.036117805602848975,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_business_ethics,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6490566037735849,0.029373646253234693,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_college_biology,5,lm-eval,vllm,,acc,none,0.6875,0.038760854559127644,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_college_computer_science,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_college_mathematics,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_college_medicine,5,lm-eval,vllm,,acc,none,0.6127167630057804,0.03714325906302067,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_college_physics,5,lm-eval,vllm,,acc,none,0.4215686274509804,0.04913595201274502,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_computer_security,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6510638297872341,0.031158522131357808,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_econometrics,5,lm-eval,vllm,,acc,none,0.5263157894736842,0.04697085136647865,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6,0.040824829046386304,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.5793650793650794,0.02542483508692397,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_formal_logic,5,lm-eval,vllm,,acc,none,0.5793650793650794,0.044154382267437474,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_biology,5,lm-eval,vllm,,acc,none,0.7483870967741936,0.02468597928624002,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6009852216748769,0.03445487686264716,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.03546563019624338,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_geography,5,lm-eval,vllm,,acc,none,0.7727272727272727,0.029857515673386438,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.844559585492228,0.026148483469153303,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6,0.02483881198803324,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.44074074074074077,0.030270671157284088,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.6932773109243697,0.029953823891886982,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_physics,5,lm-eval,vllm,,acc,none,0.4503311258278146,0.040622900186837764,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.7963302752293578,0.017266742087630755,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5694444444444444,0.03376922151252338,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7401960784313726,0.030778554678693247,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7679324894514767,0.02747974455080847,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_human_aging,5,lm-eval,vllm,,acc,none,0.6681614349775785,0.03160295143776678,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7175572519083969,0.039484061257683584,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_humanities,5,lm-eval,vllm,yes,acc,none,0.5273113708820404,0.006819610619991604,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6380368098159509,0.037757007291414395,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_machine_learning,5,lm-eval,vllm,,acc,none,0.41964285714285715,0.04684099321077107,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_management,5,lm-eval,vllm,,acc,none,0.7184466019417476,0.044532548363264673,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_marketing,5,lm-eval,vllm,,acc,none,0.7991452991452992,0.026246772946890443,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_miscellaneous,5,lm-eval,vllm,,acc,none,0.6794380587484036,0.016688893310803803,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_moral_disputes,5,lm-eval,vllm,,acc,none,0.6473988439306358,0.025722802200895838,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.2849162011173184,0.015096222302469792,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_nutrition,5,lm-eval,vllm,,acc,none,0.6928104575163399,0.02641560191438905,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_other,5,lm-eval,vllm,yes,acc,none,0.6272932088831671,0.008442042008385922,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_philosophy,5,lm-eval,vllm,,acc,none,0.6784565916398714,0.026527724079528824,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_prehistory,5,lm-eval,vllm,,acc,none,0.6635802469135802,0.026289734945952926,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_professional_accounting,5,lm-eval,vllm,,acc,none,0.35815602836879434,0.028602085862759398,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_professional_law,5,lm-eval,vllm,,acc,none,0.41590612777053454,0.012588323850313617,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6360294117647058,0.029227192460031966,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_professional_psychology,5,lm-eval,vllm,,acc,none,0.619281045751634,0.01964380155792484,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_public_relations,5,lm-eval,vllm,,acc,none,0.6363636363636364,0.04607582090719978,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_security_studies,5,lm-eval,vllm,,acc,none,0.7061224489795919,0.02916273841024971,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.704582385440364,0.008075408207775466,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_sociology,5,lm-eval,vllm,,acc,none,0.7960199004975125,0.02849317624532607,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_stem,5,lm-eval,vllm,yes,acc,none,0.5769108785283856,0.008607266850224499,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_virology,5,lm-eval,vllm,,acc,none,0.4578313253012048,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_lt_world_religions,5,lm-eval,vllm,,acc,none,0.7719298245614035,0.03218093795602355,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1332dcbfe0_2026-10-07T15-39-24.951049.json,1791387225.3944755,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl,5,lm-eval,vllm,yes,acc,none,0.6389403218914684,0.00390215266108953,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_anatomy,5,lm-eval,vllm,,acc,none,0.5037037037037037,0.04319223625811333,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_astronomy,5,lm-eval,vllm,,acc,none,0.7171052631578947,0.03665349695640767,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_business_ethics,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6566037735849056,0.02922452646912477,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_college_biology,5,lm-eval,vllm,,acc,none,0.7291666666666666,0.03716177437566019,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_college_mathematics,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_college_medicine,5,lm-eval,vllm,,acc,none,0.6184971098265896,0.03703851193099517,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_college_physics,5,lm-eval,vllm,,acc,none,0.47058823529411764,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_computer_security,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7106382978723405,0.029644006577009652,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_econometrics,5,lm-eval,vllm,,acc,none,0.5964912280701754,0.04615186962583705,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.593103448275862,0.040937939812662354,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6481481481481481,0.024594975128920938,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_formal_logic,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.044444444444444446,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_biology,5,lm-eval,vllm,,acc,none,0.7935483870967742,0.023025899617188667,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6059113300492611,0.03438157967036543,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7333333333333333,0.034531318018854146,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_geography,5,lm-eval,vllm,,acc,none,0.7474747474747475,0.030954055470365872,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7128205128205128,0.022939925418530637,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.46296296296296297,0.03040178640610153,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.028657491285071952,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_physics,5,lm-eval,vllm,,acc,none,0.48344370860927155,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8293577981651377,0.016129271025099857,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5879629629629629,0.03356787758160834,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7843137254901961,0.028867431449849337,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.810126582278481,0.025530100460233456,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_human_aging,5,lm-eval,vllm,,acc,none,0.6681614349775785,0.03160295143776678,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_human_sexuality,5,lm-eval,vllm,,acc,none,0.732824427480916,0.03880848301082397,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_humanities,5,lm-eval,vllm,yes,acc,none,0.5800212539851222,0.0068960433150938505,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.03957835471980979,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7177914110429447,0.03536117886664741,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_marketing,5,lm-eval,vllm,,acc,none,0.8632478632478633,0.022509033937077844,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_medical_genetics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7177522349936143,0.01609530296987855,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_moral_disputes,5,lm-eval,vllm,,acc,none,0.6560693641618497,0.02557412378654665,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4223463687150838,0.016519594275297204,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_nutrition,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.025646863097137932,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_other,5,lm-eval,vllm,yes,acc,none,0.652075957515288,0.008306066960115306,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_philosophy,5,lm-eval,vllm,,acc,none,0.6977491961414791,0.026082700695399676,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_prehistory,5,lm-eval,vllm,,acc,none,0.6697530864197531,0.026168298456732783,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_professional_accounting,5,lm-eval,vllm,,acc,none,0.4326241134751773,0.029555454236778834,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_professional_law,5,lm-eval,vllm,,acc,none,0.4667535853976532,0.01274197433389716,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6029411764705882,0.02972215209928001,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6683006535947712,0.019047485239360454,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_public_relations,5,lm-eval,vllm,,acc,none,0.6181818181818182,0.04653429807913508,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_security_studies,5,lm-eval,vllm,,acc,none,0.7551020408163265,0.02752963744017492,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7461813454663634,0.007743086568979126,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_stem,5,lm-eval,vllm,yes,acc,none,0.6092610212496036,0.008486781559120924,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_nl_world_religions,5,lm-eval,vllm,,acc,none,0.7485380116959064,0.03327504423846844,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d37f64a145_2026-10-07T16-04-14.234111.json,1791388698.9884257,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl,5,lm-eval,vllm,yes,acc,none,0.6170061244836917,0.003931402411582233,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.32,0.04688261722621507,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_anatomy,5,lm-eval,vllm,,acc,none,0.45925925925925926,0.04304979692464244,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_astronomy,5,lm-eval,vllm,,acc,none,0.743421052631579,0.035541803680256875,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6415094339622641,0.02951470358398169,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_college_biology,5,lm-eval,vllm,,acc,none,0.6527777777777778,0.03981240543717866,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_college_chemistry,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_college_computer_science,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_college_medicine,5,lm-eval,vllm,,acc,none,0.5895953757225434,0.03750757044895538,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_college_physics,5,lm-eval,vllm,,acc,none,0.47058823529411764,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_computer_security,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7106382978723405,0.029644006577009652,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_econometrics,5,lm-eval,vllm,,acc,none,0.5701754385964912,0.04657047260594963,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6275862068965518,0.0402873153294756,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.025107425481137254,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_biology,5,lm-eval,vllm,,acc,none,0.7967741935483871,0.022891687984554897,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6009852216748769,0.03445487686264716,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7696969696969697,0.03287666758603482,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_geography,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.03191178226713548,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8601036269430051,0.025033870583015143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6487179487179487,0.024203665177902803,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45185185185185184,0.030343862998512657,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7394957983193278,0.028510251512341933,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_physics,5,lm-eval,vllm,,acc,none,0.4503311258278146,0.040622900186837764,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8055045871559633,0.016970289090458102,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5972222222222222,0.0334488738299786,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.75,0.03039153369274154,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.810126582278481,0.025530100460233456,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_human_aging,5,lm-eval,vllm,,acc,none,0.6367713004484304,0.03227790442850494,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7022900763358778,0.04010358942462197,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_humanities,5,lm-eval,vllm,yes,acc,none,0.5519659936238045,0.006874148451892887,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_international_law,5,lm-eval,vllm,,acc,none,0.7851239669421488,0.037494924487096966,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7592592592592593,0.041331194402438355,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6319018404907976,0.037892139358383904,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_machine_learning,5,lm-eval,vllm,,acc,none,0.45535714285714285,0.04726835553719097,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_marketing,5,lm-eval,vllm,,acc,none,0.8418803418803419,0.02390232554956044,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_medical_genetics,5,lm-eval,vllm,,acc,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_miscellaneous,5,lm-eval,vllm,,acc,none,0.6883780332056194,0.016562433867284176,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_moral_disputes,5,lm-eval,vllm,,acc,none,0.6502890173410405,0.02567428145653101,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.35307262569832404,0.015984204545268537,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_nutrition,5,lm-eval,vllm,,acc,none,0.7091503267973857,0.02600480036395215,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_other,5,lm-eval,vllm,yes,acc,none,0.6363051174766656,0.008423543224745339,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_philosophy,5,lm-eval,vllm,,acc,none,0.684887459807074,0.026385273703464482,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_prehistory,5,lm-eval,vllm,,acc,none,0.6697530864197531,0.026168298456732783,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_professional_accounting,5,lm-eval,vllm,,acc,none,0.42907801418439717,0.029525914302558586,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_professional_law,5,lm-eval,vllm,,acc,none,0.4380704041720991,0.012671902782567811,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_professional_medicine,5,lm-eval,vllm,,acc,none,0.5845588235294118,0.029935342707877722,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6437908496732027,0.01937333242072444,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_public_relations,5,lm-eval,vllm,,acc,none,0.6272727272727273,0.04631381319425461,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_security_studies,5,lm-eval,vllm,,acc,none,0.726530612244898,0.028535560337128486,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7221319467013325,0.00795670177560366,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_sociology,5,lm-eval,vllm,,acc,none,0.7960199004975125,0.02849317624532607,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_stem,5,lm-eval,vllm,yes,acc,none,0.5924516333650491,0.008493515584831076,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pl_world_religions,5,lm-eval,vllm,,acc,none,0.7660818713450293,0.032467217651178305,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/26386a9388_2026-10-07T16-18-22.277544.json,1791389564.6641908,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt,5,lm-eval,vllm,yes,acc,none,0.6452784503631961,0.0038629003996664074,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_anatomy,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.04292596718256977,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_astronomy,5,lm-eval,vllm,,acc,none,0.7697368421052632,0.03426059424403165,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.660377358490566,0.029146904747798335,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_college_biology,5,lm-eval,vllm,,acc,none,0.7361111111111112,0.036856510958975304,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_college_computer_science,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_college_medicine,5,lm-eval,vllm,,acc,none,0.6416184971098265,0.0365634365335316,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_computer_security,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6936170212765957,0.03013590647851759,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6482758620689655,0.03979236637497416,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6216931216931217,0.024976954053155278,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_formal_logic,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04426266681379905,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8032258064516129,0.02261640942074208,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6403940886699507,0.0337645824650957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7696969696969697,0.03287666758603482,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_geography,5,lm-eval,vllm,,acc,none,0.803030303030303,0.02833560973246333,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8911917098445595,0.02247325333276875,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.676923076923077,0.023710888501970607,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4148148148148148,0.03003984245406923,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.726890756302521,0.0289420040409982,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_physics,5,lm-eval,vllm,,acc,none,0.46357615894039733,0.04071636065944211,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8513761467889909,0.0152512537736609,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.03324708911809121,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.803921568627451,0.027865942286639318,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.810126582278481,0.025530100460233456,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_human_aging,5,lm-eval,vllm,,acc,none,0.6771300448430493,0.031381476375754995,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_humanities,5,lm-eval,vllm,yes,acc,none,0.5832093517534538,0.00682800255443206,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_international_law,5,lm-eval,vllm,,acc,none,0.743801652892562,0.03984979653302874,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_jurisprudence,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.038935425188248496,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_machine_learning,5,lm-eval,vllm,,acc,none,0.49107142857142855,0.04745033255489126,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_medical_genetics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7343550446998723,0.015794302487888694,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_moral_disputes,5,lm-eval,vllm,,acc,none,0.6907514450867052,0.02488314057007179,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.39217877094972065,0.016329061073207363,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_nutrition,5,lm-eval,vllm,,acc,none,0.7156862745098039,0.025829163272757385,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_other,5,lm-eval,vllm,yes,acc,none,0.6626971355004828,0.008253385120930391,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_philosophy,5,lm-eval,vllm,,acc,none,0.7395498392282959,0.0249267232248456,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_prehistory,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.02492200116888636,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_professional_accounting,5,lm-eval,vllm,,acc,none,0.45390070921985815,0.029700453247291494,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_professional_law,5,lm-eval,vllm,,acc,none,0.4667535853976532,0.01274197433389716,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6176470588235294,0.029520095697687675,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_professional_psychology,5,lm-eval,vllm,,acc,none,0.696078431372549,0.018607552131279893,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_public_relations,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.04350271442923247,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_security_studies,5,lm-eval,vllm,,acc,none,0.726530612244898,0.028535560337128486,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7559311017224569,0.007620258387444753,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_sociology,5,lm-eval,vllm,,acc,none,0.8258706467661692,0.026814951200421624,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_stem,5,lm-eval,vllm,yes,acc,none,0.6127497621313035,0.008408569345811709,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_pt_world_religions,5,lm-eval,vllm,,acc,none,0.7543859649122807,0.033014059469872556,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15cc519231_2026-10-07T15-43-38.573745.json,1791387475.236313,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro,5,lm-eval,vllm,yes,acc,none,0.6356644352656317,0.003904454399722227,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_abstract_algebra,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_anatomy,5,lm-eval,vllm,,acc,none,0.5111111111111111,0.043182754919779784,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_astronomy,5,lm-eval,vllm,,acc,none,0.7368421052631579,0.03583496176361067,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6528301886792452,0.02930010170554966,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_college_biology,5,lm-eval,vllm,,acc,none,0.7291666666666666,0.03716177437566019,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_college_medicine,5,lm-eval,vllm,,acc,none,0.6011560693641619,0.03733626655383514,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_computer_security,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6893617021276596,0.03025123757921315,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_econometrics,5,lm-eval,vllm,,acc,none,0.5263157894736842,0.04697085136647865,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6275862068965518,0.0402873153294756,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6084656084656085,0.025138091388851137,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_formal_logic,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.044444444444444446,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_global_facts,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_biology,5,lm-eval,vllm,,acc,none,0.7870967741935484,0.023287665127268594,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.645320197044335,0.03366124489051447,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7454545454545455,0.03401506715249038,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_geography,5,lm-eval,vllm,,acc,none,0.7373737373737373,0.031353050095330834,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8549222797927462,0.025416343096306457,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6871794871794872,0.023507579020645396,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4740740740740741,0.030444528528810785,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.773109243697479,0.02720537153827948,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_physics,5,lm-eval,vllm,,acc,none,0.4900662251655629,0.040816771072484305,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8165137614678899,0.016595259710399303,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.03324708911809121,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7892156862745098,0.028626547912437423,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_world_history,5,lm-eval,vllm,,acc,none,0.759493670886076,0.02782078198114972,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_human_aging,5,lm-eval,vllm,,acc,none,0.6771300448430493,0.031381476375754995,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_human_sexuality,5,lm-eval,vllm,,acc,none,0.7480916030534351,0.03807387116306089,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_humanities,5,lm-eval,vllm,yes,acc,none,0.5772582359192349,0.006846247872996747,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_jurisprudence,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.04019107472557348,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7300613496932515,0.034878251684978955,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_machine_learning,5,lm-eval,vllm,,acc,none,0.4732142857142857,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_management,5,lm-eval,vllm,,acc,none,0.7087378640776699,0.044986763205729245,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_marketing,5,lm-eval,vllm,,acc,none,0.8247863247863247,0.02490443909891819,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_miscellaneous,5,lm-eval,vllm,,acc,none,0.7241379310344828,0.01598281477469557,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_moral_disputes,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.024946792225272324,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_moral_scenarios,5,lm-eval,vllm,,acc,none,0.39888268156424583,0.016376966142610156,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_nutrition,5,lm-eval,vllm,,acc,none,0.6862745098039216,0.026568921015457186,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_other,5,lm-eval,vllm,yes,acc,none,0.6485355648535565,0.008333852629373577,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_prehistory,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.025842248700902248,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_professional_accounting,5,lm-eval,vllm,,acc,none,0.4148936170212766,0.02939223658461248,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_professional_law,5,lm-eval,vllm,,acc,none,0.45371577574967403,0.012715404841277766,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_professional_medicine,5,lm-eval,vllm,,acc,none,0.6176470588235294,0.029520095697687675,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_professional_psychology,5,lm-eval,vllm,,acc,none,0.6568627450980392,0.01920660684882543,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_public_relations,5,lm-eval,vllm,,acc,none,0.6454545454545455,0.04582004841505413,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_security_studies,5,lm-eval,vllm,,acc,none,0.7428571428571429,0.027979823538744557,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_social_sciences,5,lm-eval,vllm,yes,acc,none,0.737081572960676,0.007820827468626291,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_stem,5,lm-eval,vllm,yes,acc,none,0.6111639708214399,0.008503337651025662,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_ro_world_religions,5,lm-eval,vllm,,acc,none,0.8070175438596491,0.030267457554898448,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb8ab5468_2026-10-07T16-02-06.615326.json,1791388577.764505,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr,5,lm-eval,vllm,yes,acc,none,0.5968523002421308,0.003970839602599766,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.32,0.04688261722621507,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_anatomy,5,lm-eval,vllm,,acc,none,0.5185185185185185,0.043163785995113245,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_astronomy,5,lm-eval,vllm,,acc,none,0.6842105263157895,0.03782728980865462,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_business_ethics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6075471698113207,0.030052580579557793,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_college_biology,5,lm-eval,vllm,,acc,none,0.6388888888888888,0.04016660030451229,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_college_chemistry,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_college_mathematics,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_college_medicine,5,lm-eval,vllm,,acc,none,0.6011560693641619,0.03733626655383514,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_computer_security,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6510638297872341,0.031158522131357808,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.5655172413793104,0.041307408795554966,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.02519710107424644,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_formal_logic,5,lm-eval,vllm,,acc,none,0.48412698412698413,0.044698818540726104,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_global_facts,5,lm-eval,vllm,,acc,none,0.35,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_biology,5,lm-eval,vllm,,acc,none,0.7870967741935484,0.023287665127268594,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5566502463054187,0.03495334582162933,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7636363636363637,0.03317505930009174,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7828282828282829,0.02937661648494561,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8238341968911918,0.02749350424454809,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6230769230769231,0.02457097536422601,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4888888888888889,0.030478009819615792,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.6554621848739496,0.030868682604121605,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_physics,5,lm-eval,vllm,,acc,none,0.44370860927152317,0.04056527902281736,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.7798165137614679,0.0177659786523276,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5694444444444444,0.03376922151252338,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7107843137254902,0.031822318676475524,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.810126582278481,0.025530100460233456,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_human_aging,5,lm-eval,vllm,,acc,none,0.6591928251121076,0.03181149747055356,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_human_sexuality,5,lm-eval,vllm,,acc,none,0.6717557251908397,0.041184385658063025,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_humanities,5,lm-eval,vllm,yes,acc,none,0.5360255047821466,0.006877360683903673,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.04414343666854928,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6441717791411042,0.03761521380046734,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_management,5,lm-eval,vllm,,acc,none,0.6699029126213593,0.04656147110012349,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_marketing,5,lm-eval,vllm,,acc,none,0.8376068376068376,0.024161618127987734,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_medical_genetics,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_miscellaneous,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.01726860756000581,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_moral_disputes,5,lm-eval,vllm,,acc,none,0.6763005780346821,0.02519018132760835,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3139664804469274,0.015521923933523658,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_nutrition,5,lm-eval,vllm,,acc,none,0.6993464052287581,0.026256053835718912,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_other,5,lm-eval,vllm,yes,acc,none,0.6034760218860638,0.008558358899082604,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_philosophy,5,lm-eval,vllm,,acc,none,0.6720257234726688,0.02666441088693758,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_prehistory,5,lm-eval,vllm,,acc,none,0.6265432098765432,0.02691500301138018,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_professional_accounting,5,lm-eval,vllm,,acc,none,0.4148936170212766,0.02939223658461248,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_professional_law,5,lm-eval,vllm,,acc,none,0.438722294654498,0.012673969883493123,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_professional_medicine,5,lm-eval,vllm,,acc,none,0.5257352941176471,0.030332578094555054,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6323529411764706,0.019506291693954864,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_security_studies,5,lm-eval,vllm,,acc,none,0.726530612244898,0.028535560337128486,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7029574260643484,0.008111816273310025,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_stem,5,lm-eval,vllm,yes,acc,none,0.5775451950523312,0.008580699237893688,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_virology,5,lm-eval,vllm,,acc,none,0.45180722891566266,0.0387437155658795,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sr_world_religions,5,lm-eval,vllm,,acc,none,0.6783625730994152,0.035825294425731215,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75b9d2423f_2026-10-07T16-24-37.335719.json,1791389928.971863,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv,5,lm-eval,vllm,yes,acc,none,0.6350235009257941,0.003886276919487339,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_abstract_algebra,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_anatomy,5,lm-eval,vllm,,acc,none,0.4888888888888889,0.043182754919779784,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_astronomy,5,lm-eval,vllm,,acc,none,0.7302631578947368,0.036117805602848975,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_business_ethics,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6452830188679245,0.029445175328199655,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_college_biology,5,lm-eval,vllm,,acc,none,0.7152777777777778,0.037738099906869334,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_college_chemistry,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_college_medicine,5,lm-eval,vllm,,acc,none,0.6069364161849711,0.0372424959581773,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_computer_security,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6893617021276596,0.03025123757921315,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_econometrics,5,lm-eval,vllm,,acc,none,0.5701754385964912,0.04657047260594963,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_electrical_engineering,5,lm-eval,vllm,,acc,none,0.5862068965517241,0.04104269211806236,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6216931216931217,0.024976954053155278,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_formal_logic,5,lm-eval,vllm,,acc,none,0.5396825396825397,0.04458029125470974,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_global_facts,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_biology,5,lm-eval,vllm,,acc,none,0.7903225806451613,0.023157879349083574,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5812807881773399,0.03471192860518467,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_geography,5,lm-eval,vllm,,acc,none,0.7525252525252525,0.030746300742124488,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.844559585492228,0.026148483469153303,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6923076923076923,0.023400928918310485,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4777777777777778,0.030455413985678415,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7478991596638656,0.02820554503327774,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_physics,5,lm-eval,vllm,,acc,none,0.48344370860927155,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8366972477064221,0.015848255806501524,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6064814814814815,0.033317478763703126,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.02977177522814563,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7890295358649789,0.0265583725026619,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_human_aging,5,lm-eval,vllm,,acc,none,0.7040358744394619,0.03063659134869978,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_humanities,5,lm-eval,vllm,yes,acc,none,0.5687566418703507,0.006860624128453747,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_jurisprudence,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.04330043749650743,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6441717791411042,0.03761521380046734,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_machine_learning,5,lm-eval,vllm,,acc,none,0.4375,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_marketing,5,lm-eval,vllm,,acc,none,0.8931623931623932,0.02023714900899092,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_miscellaneous,5,lm-eval,vllm,,acc,none,0.7471264367816092,0.015543377313719707,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_moral_disputes,5,lm-eval,vllm,,acc,none,0.6791907514450867,0.025131000233647866,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3776536312849162,0.01621414875213659,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_nutrition,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.025360603796242578,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_other,5,lm-eval,vllm,yes,acc,none,0.6659156742838751,0.008167592481571943,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_philosophy,5,lm-eval,vllm,,acc,none,0.707395498392283,0.02583989833487794,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_prehistory,5,lm-eval,vllm,,acc,none,0.7067901234567902,0.02532988817190095,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_professional_accounting,5,lm-eval,vllm,,acc,none,0.4219858156028369,0.029462189233370586,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_professional_law,5,lm-eval,vllm,,acc,none,0.455019556714472,0.012718456618701763,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_professional_medicine,5,lm-eval,vllm,,acc,none,0.6213235294117647,0.02946513363977605,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_professional_psychology,5,lm-eval,vllm,,acc,none,0.6421568627450981,0.019393058402355487,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_security_studies,5,lm-eval,vllm,,acc,none,0.7387755102040816,0.028123429335142832,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7419564510887228,0.007763918911614519,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_stem,5,lm-eval,vllm,yes,acc,none,0.5991119568664763,0.00851866361479257,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_sv_world_religions,5,lm-eval,vllm,,acc,none,0.7602339181286549,0.03274485211946959,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/efddd4d48b_2026-10-07T16-20-19.738129.json,1791389684.9107184,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr,5,lm-eval,vllm,yes,acc,none,0.5954992166358068,0.003983477321754373,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_anatomy,5,lm-eval,vllm,,acc,none,0.5259259259259259,0.043135316967505756,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_astronomy,5,lm-eval,vllm,,acc,none,0.631578947368421,0.03925523381052935,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_business_ethics,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6188679245283019,0.02989060968628662,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_college_biology,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03942082639927217,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_college_chemistry,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_college_medicine,5,lm-eval,vllm,,acc,none,0.5895953757225434,0.03750757044895538,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_college_physics,5,lm-eval,vllm,,acc,none,0.4019607843137255,0.04878608714466993,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_computer_security,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6127659574468085,0.031843892653395246,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_econometrics,5,lm-eval,vllm,,acc,none,0.5087719298245614,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6275862068965518,0.0402873153294756,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.5793650793650794,0.02542483508692397,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_formal_logic,5,lm-eval,vllm,,acc,none,0.5793650793650794,0.044154382267437474,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_global_facts,5,lm-eval,vllm,,acc,none,0.35,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_biology,5,lm-eval,vllm,,acc,none,0.7451612903225806,0.02479011845933226,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5812807881773399,0.03471192860518467,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.6787878787878788,0.03646204963253815,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_geography,5,lm-eval,vllm,,acc,none,0.797979797979798,0.02860620428922983,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.7616580310880829,0.030748905363909895,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.5948717948717949,0.024890471769938145,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45555555555555555,0.03036486250482447,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.6848739495798319,0.030176808288974327,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_physics,5,lm-eval,vllm,,acc,none,0.423841059602649,0.04034846678603395,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.7798165137614679,0.0177659786523276,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.5879629629629629,0.03356787758160834,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.75,0.03039153369274154,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7637130801687764,0.027652153144159246,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_human_aging,5,lm-eval,vllm,,acc,none,0.6636771300448431,0.031708824268455046,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_human_sexuality,5,lm-eval,vllm,,acc,none,0.6564885496183206,0.041649760719448814,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_humanities,5,lm-eval,vllm,yes,acc,none,0.5334750265674814,0.0068966028568036835,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_international_law,5,lm-eval,vllm,,acc,none,0.743801652892562,0.03984979653302874,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7407407407407407,0.04236511258094632,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6012269938650306,0.038470214204560226,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_machine_learning,5,lm-eval,vllm,,acc,none,0.5357142857142857,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_management,5,lm-eval,vllm,,acc,none,0.6796116504854369,0.04620284082280041,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_medical_genetics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_miscellaneous,5,lm-eval,vllm,,acc,none,0.6960408684546615,0.016448321686768987,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_moral_disputes,5,lm-eval,vllm,,acc,none,0.6416184971098265,0.025816756791584197,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3106145251396648,0.01547651543800557,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_nutrition,5,lm-eval,vllm,,acc,none,0.6633986928104575,0.0270579746244944,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_other,5,lm-eval,vllm,yes,acc,none,0.6208561313163824,0.008450773807372192,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_philosophy,5,lm-eval,vllm,,acc,none,0.6752411575562701,0.02659678228769707,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_prehistory,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.026041766202717188,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_professional_accounting,5,lm-eval,vllm,,acc,none,0.39361702127659576,0.029144544781596126,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_professional_law,5,lm-eval,vllm,,acc,none,0.43415906127770537,0.012659033237067258,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_professional_medicine,5,lm-eval,vllm,,acc,none,0.5477941176470589,0.03023375855159647,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6029411764705882,0.019794488900024096,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_security_studies,5,lm-eval,vllm,,acc,none,0.7183673469387755,0.028795185574291244,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.6860578485537862,0.008248497478705624,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_sociology,5,lm-eval,vllm,,acc,none,0.7412935323383084,0.030965903123573005,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_stem,5,lm-eval,vllm,yes,acc,none,0.5746907706945766,0.0086417615280159,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_virology,5,lm-eval,vllm,,acc,none,0.4578313253012048,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_tr_world_religions,5,lm-eval,vllm,,acc,none,0.7485380116959064,0.03327504423846844,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dc3d3a25f3_2026-10-07T15-39-20.452492.json,1791387223.0287073,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk,5,lm-eval,vllm,yes,acc,none,0.6060390257798034,0.0039760384819312,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_abstract_algebra,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_anatomy,5,lm-eval,vllm,,acc,none,0.45185185185185184,0.04299268905480864,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_astronomy,5,lm-eval,vllm,,acc,none,0.756578947368421,0.03492349668884235,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6490566037735849,0.029373646253234693,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_college_biology,5,lm-eval,vllm,,acc,none,0.6180555555555556,0.04062990784146671,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_college_mathematics,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_college_medicine,5,lm-eval,vllm,,acc,none,0.6416184971098265,0.0365634365335316,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_computer_security,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6978723404255319,0.03001755447188058,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_econometrics,5,lm-eval,vllm,,acc,none,0.5263157894736842,0.04697085136647865,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6551724137931034,0.03960933549451213,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6164021164021164,0.0250437573185202,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_formal_logic,5,lm-eval,vllm,,acc,none,0.5158730158730159,0.044698818540726104,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_biology,5,lm-eval,vllm,,acc,none,0.7580645161290323,0.024362599693031024,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.03481904844438804,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7454545454545455,0.03401506715249038,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_geography,5,lm-eval,vllm,,acc,none,0.7878787878787878,0.029126522834586777,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.7927461139896373,0.02925282329180367,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6512820512820513,0.024162780284017697,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7184873949579832,0.02921354941437222,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_physics,5,lm-eval,vllm,,acc,none,0.4503311258278146,0.040622900186837764,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_psychology,5,lm-eval,vllm,,acc,none,0.7944954128440367,0.017324352325016005,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6157407407407407,0.03317354514310747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_us_history,5,lm-eval,vllm,,acc,none,0.75,0.03039153369274154,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_world_history,5,lm-eval,vllm,,acc,none,0.7426160337552743,0.028458820991460302,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_human_aging,5,lm-eval,vllm,,acc,none,0.6681614349775785,0.03160295143776678,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_human_sexuality,5,lm-eval,vllm,,acc,none,0.7251908396946565,0.03915345408847834,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_humanities,5,lm-eval,vllm,yes,acc,none,0.5362380446333688,0.006977820937129566,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_international_law,5,lm-eval,vllm,,acc,none,0.8016528925619835,0.03640118271990949,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_jurisprudence,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.04330043749650743,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6196319018404908,0.03814269893261835,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_machine_learning,5,lm-eval,vllm,,acc,none,0.4732142857142857,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_management,5,lm-eval,vllm,,acc,none,0.7184466019417476,0.044532548363264673,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_medical_genetics,5,lm-eval,vllm,,acc,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_miscellaneous,5,lm-eval,vllm,,acc,none,0.6577266922094508,0.016967031766413575,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_moral_disputes,5,lm-eval,vllm,,acc,none,0.6502890173410405,0.02567428145653101,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_moral_scenarios,5,lm-eval,vllm,,acc,none,0.35195530726256985,0.015972668523689174,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_nutrition,5,lm-eval,vllm,,acc,none,0.7026143790849673,0.026173908506718597,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_other,5,lm-eval,vllm,yes,acc,none,0.623109108464757,0.008473663054062627,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_philosophy,5,lm-eval,vllm,,acc,none,0.6463022508038585,0.027155208103200844,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_prehistory,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.02712511551316685,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_professional_accounting,5,lm-eval,vllm,,acc,none,0.37943262411347517,0.028947338851614133,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_professional_law,5,lm-eval,vllm,,acc,none,0.4445893089960887,0.012691575792657214,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_professional_medicine,5,lm-eval,vllm,,acc,none,0.5661764705882353,0.03010563657001659,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_professional_psychology,5,lm-eval,vllm,,acc,none,0.6062091503267973,0.01976621199107302,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_security_studies,5,lm-eval,vllm,,acc,none,0.7428571428571429,0.027979823538744557,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7078323041923952,0.008085233664013342,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_sociology,5,lm-eval,vllm,,acc,none,0.7661691542288557,0.02992941540834832,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_stem,5,lm-eval,vllm,yes,acc,none,0.5940374246749128,0.008553020921737082,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_mmlu_full_uk_world_religions,5,lm-eval,vllm,,acc,none,0.6374269005847953,0.03687130615562067,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1dce64b2e8_2026-10-07T15-39-40.478723.json,1791387231.1770473,1 +v1anneal_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5c3fa91e4d_2026-10-07T16-13-35.573570.json,1791389449.3711472,1 +v1anneal_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_bytes,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5c3fa91e4d_2026-10-07T16-13-35.573570.json,1791389449.3711472,1 +v1anneal_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_norm,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5c3fa91e4d_2026-10-07T16-13-35.573570.json,1791389449.3711472,1 +v1anneal_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c288ad3366_2026-10-07T15-42-40.143290.json,1791387602.1428926,1 +v1anneal_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c288ad3366_2026-10-07T15-42-40.143290.json,1791387602.1428926,1 +v1anneal_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c288ad3366_2026-10-07T15-42-40.143290.json,1791387602.1428926,1 +v1anneal_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef877dea10_2026-10-07T15-54-58.595517.json,1791388335.3527944,1 +v1anneal_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef877dea10_2026-10-07T15-54-58.595517.json,1791388335.3527944,1 +v1anneal_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef877dea10_2026-10-07T15-54-58.595517.json,1791388335.3527944,1 +v1anneal_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/684e02b20c_2026-10-07T15-40-41.277112.json,1791387470.3679612,1 +v1anneal_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/684e02b20c_2026-10-07T15-40-41.277112.json,1791387470.3679612,1 +v1anneal_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/684e02b20c_2026-10-07T15-40-41.277112.json,1791387470.3679612,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c236ffb6f0_2026-10-07T16-13-20.362639.json,1791389440.847894,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c236ffb6f0_2026-10-07T16-13-20.362639.json,1791389440.847894,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_norm,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c236ffb6f0_2026-10-07T16-13-20.362639.json,1791389440.847894,1 +v1anneal_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac757a5eb8_2026-10-07T15-54-53.768509.json,1791388333.2711422,1 +v1anneal_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_bytes,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac757a5eb8_2026-10-07T15-54-53.768509.json,1791388333.2711422,1 +v1anneal_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac757a5eb8_2026-10-07T15-54-53.768509.json,1791388333.2711422,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/abc2c7d7e3_2026-10-07T15-40-32.034858.json,1791387470.9981997,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_bytes,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/abc2c7d7e3_2026-10-07T15-40-32.034858.json,1791387470.9981997,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_norm,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/abc2c7d7e3_2026-10-07T15-40-32.034858.json,1791387470.9981997,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc,none,0.57,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/675349088e_2026-10-07T15-55-15.388160.json,1791388339.5874221,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_bytes,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/675349088e_2026-10-07T15-55-15.388160.json,1791388339.5874221,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_norm,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/675349088e_2026-10-07T15-55-15.388160.json,1791388339.5874221,1 +v1anneal_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6c4b454995_2026-10-07T15-40-36.247546.json,1791387472.0352614,1 +v1anneal_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6c4b454995_2026-10-07T15-40-36.247546.json,1791387472.0352614,1 +v1anneal_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6c4b454995_2026-10-07T15-40-36.247546.json,1791387472.0352614,1 +v1anneal_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b5b632915c_2026-10-07T15-36-28.457549.json,1791387228.395778,1 +v1anneal_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_bytes,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b5b632915c_2026-10-07T15-36-28.457549.json,1791387228.395778,1 +v1anneal_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b5b632915c_2026-10-07T15-36-28.457549.json,1791387228.395778,1 +v1anneal_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c16af59a4a_2026-10-07T15-54-53.010458.json,1791388335.327247,1 +v1anneal_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c16af59a4a_2026-10-07T15-54-53.010458.json,1791388335.327247,1 +v1anneal_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_norm,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c16af59a4a_2026-10-07T15-54-53.010458.json,1791388335.327247,1 +v1anneal_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f1f9ea380_2026-10-07T16-01-07.251396.json,1791388701.9209473,1 +v1anneal_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f1f9ea380_2026-10-07T16-01-07.251396.json,1791388701.9209473,1 +v1anneal_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_norm,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f1f9ea380_2026-10-07T16-01-07.251396.json,1791388701.9209473,1 +v1anneal_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/caa0fded93_2026-10-07T15-42-35.467939.json,1791387591.3283095,1 +v1anneal_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/caa0fded93_2026-10-07T15-42-35.467939.json,1791387591.3283095,1 +v1anneal_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/caa0fded93_2026-10-07T15-42-35.467939.json,1791387591.3283095,1 +v1anneal_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/db8bd3129d_2026-10-07T15-54-43.625142.json,1791388325.4088812,1 +v1anneal_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_bytes,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/db8bd3129d_2026-10-07T15-54-43.625142.json,1791388325.4088812,1 +v1anneal_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_norm,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/db8bd3129d_2026-10-07T15-54-43.625142.json,1791388325.4088812,1 +v1anneal_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c0f38feae2_2026-10-07T15-40-31.174501.json,1791387471.417271,1 +v1anneal_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_bytes,none,0.56,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c0f38feae2_2026-10-07T15-40-31.174501.json,1791387471.417271,1 +v1anneal_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_norm,none,0.57,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c0f38feae2_2026-10-07T15-40-31.174501.json,1791387471.417271,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ec991f162f_2026-10-07T16-15-31.610742.json,1791389565.2528565,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ec991f162f_2026-10-07T16-15-31.610742.json,1791389565.2528565,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_norm,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ec991f162f_2026-10-07T16-15-31.610742.json,1791389565.2528565,1 +v1anneal_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/da10a9a00e_2026-10-07T15-36-31.734222.json,1791387228.597697,1 +v1anneal_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_bytes,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/da10a9a00e_2026-10-07T15-36-31.734222.json,1791387228.597697,1 +v1anneal_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_norm,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/da10a9a00e_2026-10-07T15-36-31.734222.json,1791387228.597697,1 +v1anneal_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8c34c7d488_2026-10-07T15-54-47.173592.json,1791388331.2038476,1 +v1anneal_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8c34c7d488_2026-10-07T15-54-47.173592.json,1791388331.2038476,1 +v1anneal_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8c34c7d488_2026-10-07T15-54-47.173592.json,1791388331.2038476,1 +v1anneal_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7e48973128_2026-10-07T15-57-08.736288.json,1791388463.9496887,1 +v1anneal_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7e48973128_2026-10-07T15-57-08.736288.json,1791388463.9496887,1 +v1anneal_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7e48973128_2026-10-07T15-57-08.736288.json,1791388463.9496887,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eabc1e568_2026-10-07T16-15-24.612040.json,1791389565.196754,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_bytes,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eabc1e568_2026-10-07T16-15-24.612040.json,1791389565.196754,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9eabc1e568_2026-10-07T16-15-24.612040.json,1791389565.196754,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/009df3f63c_2026-10-07T16-01-16.130870.json,1791388711.8368707,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/009df3f63c_2026-10-07T16-01-16.130870.json,1791388711.8368707,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_norm,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/009df3f63c_2026-10-07T16-01-16.130870.json,1791388711.8368707,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e91de2b08a_2026-10-07T15-54-48.707034.json,1791388335.7008603,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e91de2b08a_2026-10-07T15-54-48.707034.json,1791388335.7008603,1 +v1anneal_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_norm,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e91de2b08a_2026-10-07T15-54-48.707034.json,1791388335.7008603,1 +v1anneal_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/42cad32704_2026-10-07T15-40-33.011086.json,1791387476.358349,1 +v1anneal_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_bytes,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/42cad32704_2026-10-07T15-40-33.011086.json,1791387476.358349,1 +v1anneal_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/42cad32704_2026-10-07T15-40-33.011086.json,1791387476.358349,1 +v1anneal_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/37ed0ddeda_2026-10-07T15-54-57.021211.json,1791388330.3261318,1 +v1anneal_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_bytes,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/37ed0ddeda_2026-10-07T15-54-57.021211.json,1791388330.3261318,1 +v1anneal_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/37ed0ddeda_2026-10-07T15-54-57.021211.json,1791388330.3261318,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc72c27e25_2026-10-07T15-59-03.437588.json,1791388583.6954854,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_bytes,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc72c27e25_2026-10-07T15-59-03.437588.json,1791388583.6954854,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc72c27e25_2026-10-07T15-59-03.437588.json,1791388583.6954854,1 +v1anneal_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8d5acd1b9_2026-10-07T15-57-01.341902.json,1791388459.121746,1 +v1anneal_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8d5acd1b9_2026-10-07T15-57-01.341902.json,1791388459.121746,1 +v1anneal_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b8d5acd1b9_2026-10-07T15-57-01.341902.json,1791388459.121746,1 +v1anneal_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/25e4136f72_2026-10-07T16-19-31.500013.json,1791389804.1379964,1 +v1anneal_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/25e4136f72_2026-10-07T16-19-31.500013.json,1791389804.1379964,1 +v1anneal_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/25e4136f72_2026-10-07T16-19-31.500013.json,1791389804.1379964,1 +v1anneal_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69bb73ebae_2026-10-07T15-36-33.744343.json,1791387223.2755337,1 +v1anneal_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69bb73ebae_2026-10-07T15-36-33.744343.json,1791387223.2755337,1 +v1anneal_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69bb73ebae_2026-10-07T15-36-33.744343.json,1791387223.2755337,1 +v1anneal_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc,none,0.92,0.027265992434429072,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/42603d3e84_2026-10-07T15-56-54.873200.json,1791388456.743382,1 +v1anneal_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.94,0.023868325657594204,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/42603d3e84_2026-10-07T15-56-54.873200.json,1791388456.743382,1 +v1anneal_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_norm,none,0.93,0.02564323999762428,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/42603d3e84_2026-10-07T15-56-54.873200.json,1791388456.743382,1 +v1anneal_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4b7f82c87_2026-10-07T15-40-41.481803.json,1791387478.0593424,1 +v1anneal_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4b7f82c87_2026-10-07T15-40-41.481803.json,1791387478.0593424,1 +v1anneal_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_norm,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e4b7f82c87_2026-10-07T15-40-41.481803.json,1791387478.0593424,1 +v1anneal_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/23081e0e59_2026-10-07T15-40-34.367403.json,1791387473.7677286,1 +v1anneal_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/23081e0e59_2026-10-07T15-40-34.367403.json,1791387473.7677286,1 +v1anneal_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/23081e0e59_2026-10-07T15-40-34.367403.json,1791387473.7677286,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0245a40a8_2026-10-07T16-19-39.050654.json,1791389810.8565028,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0245a40a8_2026-10-07T16-19-39.050654.json,1791389810.8565028,1 +v1anneal_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0245a40a8_2026-10-07T16-19-39.050654.json,1791389810.8565028,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_als_latn,0,lm-eval,vllm,,exact_match,strict_match,0.35,0.047937248544110196,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/833c0d6932_2026-10-07T15-54-58.813194.json,1791388332.5654805,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_bos_latn,0,lm-eval,vllm,,exact_match,strict_match,0.58,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4386799264_2026-10-07T15-42-37.713678.json,1791387595.3308952,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_bul_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/083dcd7f17_2026-10-07T15-42-38.570247.json,1791387595.2171955,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_cat_latn,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.049236596391733084,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b08e0660b8_2026-10-07T15-42-48.391064.json,1791387599.1323469,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_ces_latn,0,lm-eval,vllm,,exact_match,strict_match,0.55,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/950a68c326_2026-10-07T15-42-36.116098.json,1791387594.5719905,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_deu_latn,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.049756985195624284,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/95b56007f3_2026-10-07T15-40-37.424282.json,1791387472.3569744,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_ekk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.35,0.0479372485441102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fd58ace4d0_2026-10-07T15-40-51.493817.json,1791387477.8981454,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_ell_grek,0,lm-eval,vllm,,exact_match,strict_match,0.38,0.048783173121456316,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a488833588_2026-10-07T16-01-11.100382.json,1791388704.875425,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_eng_latn,0,lm-eval,vllm,,exact_match,strict_match,0.34,0.04760952285695236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f295dd0ce9_2026-10-07T15-54-58.672787.json,1791388331.305163,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_fin_latn,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.049236596391733084,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef06557782_2026-10-07T16-01-15.825758.json,1791388703.4412415,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_fra_latn_fran,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7b6ae1b635_2026-10-07T15-36-27.860431.json,1791387224.3490083,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_glg_latn,0,lm-eval,vllm,,exact_match,strict_match,0.24,0.042923469599092816,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1ff12f5e19_2026-10-07T16-15-26.473141.json,1791389565.0038407,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_hrv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956911,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d5d56330a1_2026-10-07T15-54-56.723225.json,1791388330.4054637,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_hun_latn,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d536d0d31e_2026-10-07T15-41-02.925160.json,1791387471.4538634,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_isl_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/625a313de4_2026-10-07T16-19-37.761615.json,1791389804.6835275,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_ita_latn,0,lm-eval,vllm,,exact_match,strict_match,0.33,0.047258156262526045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ac094a8ef4_2026-10-07T16-15-33.312272.json,1791389564.6061907,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_kat_geor,0,lm-eval,vllm,,exact_match,strict_match,0.13,0.033799766898963086,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/946a11f2ce_2026-10-07T16-13-37.464931.json,1791389442.077287,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_lit_latn,0,lm-eval,vllm,,exact_match,strict_match,0.44,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b86594dbcf_2026-10-07T15-54-59.334755.json,1791388333.3610992,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_mkd_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a16ef93435_2026-10-07T15-59-12.572969.json,1791388578.4134943,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_nld_latn,0,lm-eval,vllm,,exact_match,strict_match,0.53,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/01d33485e2_2026-10-07T15-59-02.694527.json,1791388575.5697083,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_nno_latn,0,lm-eval,vllm,,exact_match,strict_match,0.48,0.050211673156867795,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1c744731f0_2026-10-07T15-57-02.895036.json,1791388453.2721276,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_nob_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bd727d750c_2026-10-07T15-42-49.730514.json,1791387593.0463006,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_pol_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/07a8d9bce0_2026-10-07T15-54-58.140550.json,1791388329.9414065,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_por_latn_port,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001975,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83e169ac28_2026-10-07T15-36-35.289717.json,1791387224.665748,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_ron_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/91c79fcf58_2026-10-07T15-59-12.800638.json,1791388578.9380338,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_slk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.31,0.04648231987117316,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/109635b8f3_2026-10-07T15-42-41.303088.json,1791387592.8960931,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_slv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.04999999999999999,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3963d40a61_2026-10-07T15-42-42.744726.json,1791387594.847466,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_spa_latn_spai,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/105012bcc0_2026-10-07T15-59-04.386906.json,1791388577.2194686,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_srp_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.37,0.048523658709391,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f08a299eee_2026-10-07T15-54-51.973909.json,1791388330.3023398,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_swe_latn,0,lm-eval,vllm,,exact_match,strict_match,0.38,0.048783173121456316,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93bfdcad19_2026-10-07T15-57-13.724938.json,1791388462.0217211,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_tur_latn,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51b36fdfca_2026-10-07T15-40-44.482138.json,1791387481.2852042,1 +v1anneal_merge3_116k_120k,global_piqa_prompted_ukr_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.35,0.0479372485441102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/680c3c23ea_2026-10-07T15-40-43.533956.json,1791387476.4341984,1 +v1anneal_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,flexible-extract,0.7968157695223654,0.011083227665267795,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4dc30fa5a6_2026-10-07T15-41-52.581572.json,1791387477.9718115,1 +v1anneal_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,strict-match,0.7937831690674754,0.011144364089781433,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4dc30fa5a6_2026-10-07T15-41-52.581572.json,1791387477.9718115,1 +v1anneal_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc,none,0.586337382991436,0.004914829384983438,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/962260c322_2026-10-07T15-44-04.662333.json,1791387598.1951709,1 +v1anneal_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc_norm,none,0.7781318462457678,0.004146537488135847,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/962260c322_2026-10-07T15-44-04.662333.json,1791387598.1951709,1 +v1anneal_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc,none,0.6080462059350727,0.004871887422893928,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8316c6d2f7_2026-10-07T16-20-16.107887.json,1791389444.458647,1 +v1anneal_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc_norm,none,0.8098984266082454,0.003915792315457554,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8316c6d2f7_2026-10-07T16-20-16.107887.json,1791389444.458647,1 +v1anneal_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc,none,0.49603734665074367,0.005209865957816805,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98890a06e6_2026-10-07T15-56-30.772988.json,1791388338.580777,1 +v1anneal_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc_norm,none,0.6482466616002606,0.004975760215318363,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/98890a06e6_2026-10-07T15-56-30.772988.json,1791388338.580777,1 +v1anneal_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc,none,0.5170338527673294,0.005180634867365788,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/295e5bf9b5_2026-10-07T16-00-31.045749.json,1791388576.4603589,1 +v1anneal_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc_norm,none,0.6804943578721118,0.004834111678894642,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/295e5bf9b5_2026-10-07T16-00-31.045749.json,1791388576.4603589,1 +v1anneal_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc,none,0.519000853970965,0.005162450836440469,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c02504f1f5_2026-10-07T15-56-35.093581.json,1791388341.2404068,1 +v1anneal_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc_norm,none,0.669406490179334,0.004860622141423822,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c02504f1f5_2026-10-07T15-56-35.093581.json,1791388341.2404068,1 +v1anneal_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc,none,0.5445914230851291,0.005143949459775902,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0713d5e892_2026-10-07T15-37-55.561051.json,1791387226.4799562,1 +v1anneal_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc_norm,none,0.7141028376360145,0.004667088038169336,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0713d5e892_2026-10-07T15-37-55.561051.json,1791387226.4799562,1 +v1anneal_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc,none,0.29735278227984874,0.004751600519202667,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/52fef1bd0f_2026-10-07T16-22-53.971565.json,1791389927.3244798,1 +v1anneal_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc_norm,none,0.35548352242031334,0.0049757895343298,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/52fef1bd0f_2026-10-07T16-22-53.971565.json,1791389927.3244798,1 +v1anneal_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc,none,0.5359820089955023,0.0051610591494622915,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/76b018f3ae_2026-10-07T15-38-01.675363.json,1791387225.2988856,1 +v1anneal_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc_norm,none,0.7104304990361962,0.004693896705514171,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/76b018f3ae_2026-10-07T15-38-01.675363.json,1791387225.2988856,1 +v1anneal_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc,none,0.48474289937704573,0.005135618223603086,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f3f7fdb0b_2026-10-07T15-56-38.090862.json,1791388342.0513942,1 +v1anneal_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc_norm,none,0.6391088586210537,0.0049351520771521926,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f3f7fdb0b_2026-10-07T15-56-38.090862.json,1791388342.0513942,1 +v1anneal_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc,none,0.43765763789889245,0.005195386511651058,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/916df9dc88_2026-10-07T15-56-25.912363.json,1791388327.348642,1 +v1anneal_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc_norm,none,0.5679350806009431,0.005187690485711023,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/916df9dc88_2026-10-07T15-56-25.912363.json,1791388327.348642,1 +v1anneal_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc,none,0.520395953442837,0.005210787551450236,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/16ad411ea6_2026-10-07T16-16-38.504736.json,1791389558.756385,1 +v1anneal_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc_norm,none,0.6841074730773414,0.004848716984130661,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/16ad411ea6_2026-10-07T16-16-38.504736.json,1791389558.756385,1 +v1anneal_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc,none,0.5172153264975715,0.005191742652274083,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d24ac49920_2026-10-07T15-56-21.982886.json,1791388336.9699602,1 +v1anneal_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc_norm,none,0.6765245547760389,0.004860301027225636,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d24ac49920_2026-10-07T15-56-21.982886.json,1791388336.9699602,1 +v1anneal_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc,none,0.5286596597681222,0.005196388328272962,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9f5014e46_2026-10-07T16-16-52.331766.json,1791389559.1969442,1 +v1anneal_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc_norm,none,0.7009426806804637,0.004766116762571794,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9f5014e46_2026-10-07T16-16-52.331766.json,1791389559.1969442,1 +v1anneal_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc,none,0.5021092482422931,0.005200393078707539,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3aef50581f_2026-10-07T15-42-10.575669.json,1791387469.1999202,1 +v1anneal_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc_norm,none,0.651487290427258,0.004956011617309783,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3aef50581f_2026-10-07T15-42-10.575669.json,1791387469.1999202,1 +v1anneal_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc,none,0.46146547179757513,0.005118946725393451,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b28dad6a3f_2026-10-07T15-44-11.726671.json,1791387598.17979,1 +v1anneal_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc_norm,none,0.599367422245651,0.005031806420528823,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b28dad6a3f_2026-10-07T15-44-11.726671.json,1791387598.17979,1 +v1anneal_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc,none,0.48565985818605145,0.00514187331328295,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0efd3ffd65_2026-10-07T16-02-39.805037.json,1791388704.9412093,1 +v1anneal_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc_norm,none,0.6369986241930363,0.004947131338999468,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0efd3ffd65_2026-10-07T16-02-39.805037.json,1791388704.9412093,1 +v1anneal_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc,none,0.5187458890594168,0.005231706022437107,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0af99cf552_2026-10-07T16-18-56.822410.json,1791389682.9794166,1 +v1anneal_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc_norm,none,0.6815391361543521,0.004878116930009495,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0af99cf552_2026-10-07T16-18-56.822410.json,1791389682.9794166,1 +v1anneal_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc,none,0.4586034647677755,0.005137215064747397,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/88486a98de_2026-10-07T16-00-42.765175.json,1791388577.725544,1 +v1anneal_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc_norm,none,0.593261770645127,0.005064446926963973,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/88486a98de_2026-10-07T16-00-42.765175.json,1791388577.725544,1 +v1anneal_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_loose_acc,none,0.34292565947242204,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/02d96659dc_2026-10-07T15-38-29.434513.json,1791387223.0604053,1 +v1anneal_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_strict_acc,none,0.3261390887290168,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/02d96659dc_2026-10-07T15-38-29.434513.json,1791387223.0604053,1 +v1anneal_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_loose_acc,none,0.21072088724584104,0.017549801883664215,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/02d96659dc_2026-10-07T15-38-29.434513.json,1791387223.0604053,1 +v1anneal_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_strict_acc,none,0.20147874306839186,0.017260802262371536,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/02d96659dc_2026-10-07T15-38-29.434513.json,1791387223.0604053,1 +v1anneal_merge3_116k_120k,include_base_44_albanian,0,lm-eval,vllm,yes,acc,none,0.7223230490018149,0.018934277907395117,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e9d68a4d55_2026-10-07T15-59-09.126339.json,1791388582.8862042,1 +v1anneal_merge3_116k_120k,include_base_44_albanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.7623318385650224,0.02856807946471428,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e9d68a4d55_2026-10-07T15-59-09.126339.json,1791388582.8862042,1 +v1anneal_merge3_116k_120k,include_base_44_albanian_business_commerce,0,lm-eval,vllm,,acc,none,0.6995515695067265,0.030769352008229164,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e9d68a4d55_2026-10-07T15-59-09.126339.json,1791388582.8862042,1 +v1anneal_merge3_116k_120k,include_base_44_albanian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.52,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e9d68a4d55_2026-10-07T15-59-09.126339.json,1791388582.8862042,1 +v1anneal_merge3_116k_120k,include_base_44_albanian_social_science,0,lm-eval,vllm,,acc,none,0.8181818181818182,0.0524863881081478,55,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e9d68a4d55_2026-10-07T15-59-09.126339.json,1791388582.8862042,1 +v1anneal_merge3_116k_120k,include_base_44_albanian_stem,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e9d68a4d55_2026-10-07T15-59-09.126339.json,1791388582.8862042,1 +v1anneal_merge3_116k_120k,include_base_44_basque,0,lm-eval,vllm,yes,acc,none,0.422,0.022109039310618563,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f29f175cca_2026-10-07T16-01-11.717171.json,1791388705.1730952,1 +v1anneal_merge3_116k_120k,include_base_44_basque_professional_certification,0,lm-eval,vllm,,acc,none,0.422,0.022109039310618563,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f29f175cca_2026-10-07T16-01-11.717171.json,1791388705.1730952,1 +v1anneal_merge3_116k_120k,include_base_44_bulgarian,0,lm-eval,vllm,yes,acc,none,0.6527272727272727,0.020185281045417714,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51edb72dba_2026-10-07T15-40-29.628822.json,1791387469.2197099,1 +v1anneal_merge3_116k_120k,include_base_44_bulgarian_arts_humanities,0,lm-eval,vllm,,acc,none,0.72,0.02845414827783231,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51edb72dba_2026-10-07T15-40-29.628822.json,1791387469.2197099,1 +v1anneal_merge3_116k_120k,include_base_44_bulgarian_social_science,0,lm-eval,vllm,,acc,none,0.6,0.031046021028253316,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51edb72dba_2026-10-07T15-40-29.628822.json,1791387469.2197099,1 +v1anneal_merge3_116k_120k,include_base_44_bulgarian_stem,0,lm-eval,vllm,,acc,none,0.58,0.07050835816716038,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/51edb72dba_2026-10-07T15-40-29.628822.json,1791387469.2197099,1 +v1anneal_merge3_116k_120k,include_base_44_croatian,0,lm-eval,vllm,yes,acc,none,0.7054545454545454,0.019315871069847466,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/53988cff6d_2026-10-07T15-36-34.649297.json,1791387225.2390616,1 +v1anneal_merge3_116k_120k,include_base_44_croatian_arts_humanities,0,lm-eval,vllm,,acc,none,0.652,0.030186568464511673,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/53988cff6d_2026-10-07T15-36-34.649297.json,1791387225.2390616,1 +v1anneal_merge3_116k_120k,include_base_44_croatian_social_science,0,lm-eval,vllm,,acc,none,0.772,0.026587432487268498,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/53988cff6d_2026-10-07T15-36-34.649297.json,1791387225.2390616,1 +v1anneal_merge3_116k_120k,include_base_44_croatian_stem,0,lm-eval,vllm,,acc,none,0.64,0.06857142857142857,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/53988cff6d_2026-10-07T15-36-34.649297.json,1791387225.2390616,1 +v1anneal_merge3_116k_120k,include_base_44_dutch,0,lm-eval,vllm,yes,acc,none,0.6460980036297641,0.020296280886919784,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/90b7ea4057_2026-10-07T15-55-06.090120.json,1791388337.7394352,1 +v1anneal_merge3_116k_120k,include_base_44_dutch_applied_science,0,lm-eval,vllm,,acc,none,0.9333333333333333,0.06666666666666665,15,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/90b7ea4057_2026-10-07T15-55-06.090120.json,1791388337.7394352,1 +v1anneal_merge3_116k_120k,include_base_44_dutch_arts_humanities,0,lm-eval,vllm,,acc,none,0.6584362139917695,0.03048492149265,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/90b7ea4057_2026-10-07T15-55-06.090120.json,1791388337.7394352,1 +v1anneal_merge3_116k_120k,include_base_44_dutch_health_oriented_education,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/90b7ea4057_2026-10-07T15-55-06.090120.json,1791388337.7394352,1 +v1anneal_merge3_116k_120k,include_base_44_dutch_social_science,0,lm-eval,vllm,,acc,none,0.6296296296296297,0.03104223722994238,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/90b7ea4057_2026-10-07T15-55-06.090120.json,1791388337.7394352,1 +v1anneal_merge3_116k_120k,include_base_44_dutch_stem,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/90b7ea4057_2026-10-07T15-55-06.090120.json,1791388337.7394352,1 +v1anneal_merge3_116k_120k,include_base_44_estonian,0,lm-eval,vllm,yes,acc,none,0.5758928571428571,0.0325273790057567,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f677979cd4_2026-10-07T16-13-21.057939.json,1791389437.2888193,1 +v1anneal_merge3_116k_120k,include_base_44_estonian_applied_science,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.09705231721239392,14,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f677979cd4_2026-10-07T16-13-21.057939.json,1791389437.2888193,1 +v1anneal_merge3_116k_120k,include_base_44_estonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.515527950310559,0.03950940416210684,161,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f677979cd4_2026-10-07T16-13-21.057939.json,1791389437.2888193,1 +v1anneal_merge3_116k_120k,include_base_44_estonian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5,0.5,2,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f677979cd4_2026-10-07T16-13-21.057939.json,1791389437.2888193,1 +v1anneal_merge3_116k_120k,include_base_44_estonian_social_science,0,lm-eval,vllm,,acc,none,0.5454545454545454,0.1574591643244434,11,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f677979cd4_2026-10-07T16-13-21.057939.json,1791389437.2888193,1 +v1anneal_merge3_116k_120k,include_base_44_estonian_stem,0,lm-eval,vllm,,acc,none,0.75,0.07319250547113999,36,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f677979cd4_2026-10-07T16-13-21.057939.json,1791389437.2888193,1 +v1anneal_merge3_116k_120k,include_base_44_finnish,0,lm-eval,vllm,yes,acc,none,0.4791288566243194,0.02132470097727771,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0c74f2256_2026-10-07T15-36-32.657052.json,1791387226.0393386,1 +v1anneal_merge3_116k_120k,include_base_44_finnish_applied_science,0,lm-eval,vllm,,acc,none,0.4827586206896552,0.09443492370778726,29,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0c74f2256_2026-10-07T15-36-32.657052.json,1791387226.0393386,1 +v1anneal_merge3_116k_120k,include_base_44_finnish_arts_humanities,0,lm-eval,vllm,,acc,none,0.4646017699115044,0.03324969275090135,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0c74f2256_2026-10-07T15-36-32.657052.json,1791387226.0393386,1 +v1anneal_merge3_116k_120k,include_base_44_finnish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.4666666666666667,0.07521014330903548,45,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0c74f2256_2026-10-07T15-36-32.657052.json,1791387226.0393386,1 +v1anneal_merge3_116k_120k,include_base_44_finnish_social_science,0,lm-eval,vllm,,acc,none,0.4778761061946903,0.033300686234029694,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0c74f2256_2026-10-07T15-36-32.657052.json,1791387226.0393386,1 +v1anneal_merge3_116k_120k,include_base_44_finnish_stem,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d0c74f2256_2026-10-07T15-36-32.657052.json,1791387226.0393386,1 +v1anneal_merge3_116k_120k,include_base_44_french,0,lm-eval,vllm,yes,acc,none,0.5966587112171837,0.023997238632423895,419,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fbabf7f4cf_2026-10-07T15-54-53.160303.json,1791388327.565771,1 +v1anneal_merge3_116k_120k,include_base_44_french_arts_humanities,0,lm-eval,vllm,,acc,none,0.6278195488721805,0.029694174698784492,266,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fbabf7f4cf_2026-10-07T15-54-53.160303.json,1791388327.565771,1 +v1anneal_merge3_116k_120k,include_base_44_french_driving_license,0,lm-eval,vllm,,acc,none,0.5319148936170213,0.07357064625618347,47,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fbabf7f4cf_2026-10-07T15-54-53.160303.json,1791388327.565771,1 +v1anneal_merge3_116k_120k,include_base_44_french_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5625,0.128086884574495,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fbabf7f4cf_2026-10-07T15-54-53.160303.json,1791388327.565771,1 +v1anneal_merge3_116k_120k,include_base_44_french_social_science,0,lm-eval,vllm,,acc,none,0.5675675675675675,0.05798377475143101,74,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fbabf7f4cf_2026-10-07T15-54-53.160303.json,1791388327.565771,1 +v1anneal_merge3_116k_120k,include_base_44_french_stem,0,lm-eval,vllm,,acc,none,0.4375,0.128086884574495,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fbabf7f4cf_2026-10-07T15-54-53.160303.json,1791388327.565771,1 +v1anneal_merge3_116k_120k,include_base_44_georgian,0,lm-eval,vllm,yes,acc,none,0.434,0.02218721580302901,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/20a834363e_2026-10-07T15-40-46.046401.json,1791387474.1224246,1 +v1anneal_merge3_116k_120k,include_base_44_georgian_arts_humanities,0,lm-eval,vllm,,acc,none,0.434,0.02218721580302901,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/20a834363e_2026-10-07T15-40-46.046401.json,1791387474.1224246,1 +v1anneal_merge3_116k_120k,include_base_44_german,0,lm-eval,vllm,yes,acc,none,0.4676258992805755,0.042602193688082754,139,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a504c1bf4b_2026-10-07T15-42-28.406931.json,1791387587.9847944,1 +v1anneal_merge3_116k_120k,include_base_44_german_driving_license,0,lm-eval,vllm,,acc,none,0.5652173913043478,0.10568965974008647,23,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a504c1bf4b_2026-10-07T15-42-28.406931.json,1791387587.9847944,1 +v1anneal_merge3_116k_120k,include_base_44_german_social_science,0,lm-eval,vllm,,acc,none,0.43956043956043955,0.052318156985661904,91,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a504c1bf4b_2026-10-07T15-42-28.406931.json,1791387587.9847944,1 +v1anneal_merge3_116k_120k,include_base_44_german_stem,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a504c1bf4b_2026-10-07T15-42-28.406931.json,1791387587.9847944,1 +v1anneal_merge3_116k_120k,include_base_44_greek,0,lm-eval,vllm,yes,acc,none,0.519927536231884,0.021124906979672987,552,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f81c92c75_2026-10-07T15-57-01.663223.json,1791388457.5974162,1 +v1anneal_merge3_116k_120k,include_base_44_greek_arts_humanities,0,lm-eval,vllm,,acc,none,0.4594594594594595,0.08305895907471071,37,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f81c92c75_2026-10-07T15-57-01.663223.json,1791388457.5974162,1 +v1anneal_merge3_116k_120k,include_base_44_greek_business_commerce,0,lm-eval,vllm,,acc,none,0.6666666666666666,0.05986843400892496,63,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f81c92c75_2026-10-07T15-57-01.663223.json,1791388457.5974162,1 +v1anneal_merge3_116k_120k,include_base_44_greek_health_oriented_education,0,lm-eval,vllm,,acc,none,0.44,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f81c92c75_2026-10-07T15-57-01.663223.json,1791388457.5974162,1 +v1anneal_merge3_116k_120k,include_base_44_greek_medical_license,0,lm-eval,vllm,,acc,none,0.5373134328358209,0.043234602868397205,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f81c92c75_2026-10-07T15-57-01.663223.json,1791388457.5974162,1 +v1anneal_merge3_116k_120k,include_base_44_greek_professional_certification,0,lm-eval,vllm,,acc,none,0.417910447761194,0.042767188024559935,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f81c92c75_2026-10-07T15-57-01.663223.json,1791388457.5974162,1 +v1anneal_merge3_116k_120k,include_base_44_greek_social_science,0,lm-eval,vllm,,acc,none,0.5746268656716418,0.04286987049655245,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f81c92c75_2026-10-07T15-57-01.663223.json,1791388457.5974162,1 +v1anneal_merge3_116k_120k,include_base_44_greek_stem,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2f81c92c75_2026-10-07T15-57-01.663223.json,1791388457.5974162,1 +v1anneal_merge3_116k_120k,include_base_44_hungarian,0,lm-eval,vllm,yes,acc,none,0.48545454545454547,0.021320702066334456,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/12d6eb39bb_2026-10-07T16-19-24.818989.json,1791389804.235727,1 +v1anneal_merge3_116k_120k,include_base_44_hungarian_applied_science,0,lm-eval,vllm,,acc,none,0.4780058651026393,0.027090059932517726,341,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/12d6eb39bb_2026-10-07T16-19-24.818989.json,1791389804.235727,1 +v1anneal_merge3_116k_120k,include_base_44_hungarian_social_science,0,lm-eval,vllm,,acc,none,0.4782608695652174,0.036926112179582665,184,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/12d6eb39bb_2026-10-07T16-19-24.818989.json,1791389804.235727,1 +v1anneal_merge3_116k_120k,include_base_44_hungarian_stem,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/12d6eb39bb_2026-10-07T16-19-24.818989.json,1791389804.235727,1 +v1anneal_merge3_116k_120k,include_base_44_italian,0,lm-eval,vllm,yes,acc,none,0.6478102189781022,0.020252604381443527,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d5ffab0bf_2026-10-07T15-40-33.448230.json,1791387471.909965,1 +v1anneal_merge3_116k_120k,include_base_44_italian_applied_science,0,lm-eval,vllm,,acc,none,0.6285714285714286,0.0828658355335869,35,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d5ffab0bf_2026-10-07T15-40-33.448230.json,1791387471.909965,1 +v1anneal_merge3_116k_120k,include_base_44_italian_arts_humanities,0,lm-eval,vllm,,acc,none,0.5868263473053892,0.03821792185198407,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d5ffab0bf_2026-10-07T15-40-33.448230.json,1791387471.909965,1 +v1anneal_merge3_116k_120k,include_base_44_italian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.8333333333333334,0.11236664374387369,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d5ffab0bf_2026-10-07T15-40-33.448230.json,1791387471.909965,1 +v1anneal_merge3_116k_120k,include_base_44_italian_professional_certification,0,lm-eval,vllm,,acc,none,0.5935483870967742,0.03957966643707446,155,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d5ffab0bf_2026-10-07T15-40-33.448230.json,1791387471.909965,1 +v1anneal_merge3_116k_120k,include_base_44_italian_social_science,0,lm-eval,vllm,,acc,none,0.7485029940119761,0.033675118801687005,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d5ffab0bf_2026-10-07T15-40-33.448230.json,1791387471.909965,1 +v1anneal_merge3_116k_120k,include_base_44_italian_stem,0,lm-eval,vllm,,acc,none,0.6666666666666666,0.1421338109037403,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d5ffab0bf_2026-10-07T15-40-33.448230.json,1791387471.909965,1 +v1anneal_merge3_116k_120k,include_base_44_lithuanian,0,lm-eval,vllm,yes,acc,none,0.649812734082397,0.020606241645129756,534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d387bcc5ae_2026-10-07T15-40-37.103864.json,1791387472.7484555,1 +v1anneal_merge3_116k_120k,include_base_44_lithuanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6507462686567164,0.02608573855474172,335,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d387bcc5ae_2026-10-07T15-40-37.103864.json,1791387472.7484555,1 +v1anneal_merge3_116k_120k,include_base_44_lithuanian_business_commerce,0,lm-eval,vllm,,acc,none,0.5,0.08006407690254357,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d387bcc5ae_2026-10-07T15-40-37.103864.json,1791387472.7484555,1 +v1anneal_merge3_116k_120k,include_base_44_lithuanian_professional_certification,0,lm-eval,vllm,,acc,none,0.6041666666666666,0.0713322023838232,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d387bcc5ae_2026-10-07T15-40-37.103864.json,1791387472.7484555,1 +v1anneal_merge3_116k_120k,include_base_44_lithuanian_social_science,0,lm-eval,vllm,,acc,none,0.7142857142857143,0.05181973215071512,77,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d387bcc5ae_2026-10-07T15-40-37.103864.json,1791387472.7484555,1 +v1anneal_merge3_116k_120k,include_base_44_lithuanian_stem,0,lm-eval,vllm,,acc,none,0.7352941176470589,0.07679896586280788,34,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d387bcc5ae_2026-10-07T15-40-37.103864.json,1791387472.7484555,1 +v1anneal_merge3_116k_120k,include_base_44_north macedonian,0,lm-eval,vllm,yes,acc,none,0.7803992740471869,0.017466149218617177,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/67fc540e9a_2026-10-07T15-54-55.153846.json,1791388333.9069803,1 +v1anneal_merge3_116k_120k,include_base_44_north macedonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.8258928571428571,0.025393216641551683,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/67fc540e9a_2026-10-07T15-54-55.153846.json,1791388333.9069803,1 +v1anneal_merge3_116k_120k,include_base_44_north macedonian_business_commerce,0,lm-eval,vllm,,acc,none,0.7767857142857143,0.02788426339613535,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/67fc540e9a_2026-10-07T15-54-55.153846.json,1791388333.9069803,1 +v1anneal_merge3_116k_120k,include_base_44_north macedonian_social_science,0,lm-eval,vllm,,acc,none,0.7924528301886793,0.05623975840347623,53,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/67fc540e9a_2026-10-07T15-54-55.153846.json,1791388333.9069803,1 +v1anneal_merge3_116k_120k,include_base_44_north macedonian_stem,0,lm-eval,vllm,,acc,none,0.58,0.07050835816716038,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/67fc540e9a_2026-10-07T15-54-55.153846.json,1791388333.9069803,1 +v1anneal_merge3_116k_120k,include_base_44_polish,0,lm-eval,vllm,yes,acc,none,0.572992700729927,0.020971098264292103,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b2f884f32d_2026-10-07T15-58-59.593133.json,1791388576.571787,1 +v1anneal_merge3_116k_120k,include_base_44_polish_professional_certification,0,lm-eval,vllm,,acc,none,0.5887096774193549,0.022116797087243237,496,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b2f884f32d_2026-10-07T15-58-59.593133.json,1791388576.571787,1 +v1anneal_merge3_116k_120k,include_base_44_polish_social_science,0,lm-eval,vllm,,acc,none,1.0,0.0,4,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b2f884f32d_2026-10-07T15-58-59.593133.json,1791388576.571787,1 +v1anneal_merge3_116k_120k,include_base_44_polish_stem,0,lm-eval,vllm,,acc,none,0.375,0.07061658535825402,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b2f884f32d_2026-10-07T15-58-59.593133.json,1791388576.571787,1 +v1anneal_merge3_116k_120k,include_base_44_portuguese,0,lm-eval,vllm,yes,acc,none,0.5644283121597096,0.020596689278803596,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6c016ba77_2026-10-07T15-55-04.318496.json,1791388336.5600789,1 +v1anneal_merge3_116k_120k,include_base_44_portuguese_applied_science,0,lm-eval,vllm,,acc,none,0.4642857142857143,0.05474194552581068,84,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6c016ba77_2026-10-07T15-55-04.318496.json,1791388336.5600789,1 +v1anneal_merge3_116k_120k,include_base_44_portuguese_arts_humanities,0,lm-eval,vllm,,acc,none,0.6363636363636364,0.03889023926786351,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6c016ba77_2026-10-07T15-55-04.318496.json,1791388336.5600789,1 +v1anneal_merge3_116k_120k,include_base_44_portuguese_business_commerce,0,lm-eval,vllm,,acc,none,0.3333333333333333,0.055945423886445945,72,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6c016ba77_2026-10-07T15-55-04.318496.json,1791388336.5600789,1 +v1anneal_merge3_116k_120k,include_base_44_portuguese_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5806451612903226,0.06318024670039094,62,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6c016ba77_2026-10-07T15-55-04.318496.json,1791388336.5600789,1 +v1anneal_merge3_116k_120k,include_base_44_portuguese_social_science,0,lm-eval,vllm,,acc,none,0.6753246753246753,0.03785604468377516,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6c016ba77_2026-10-07T15-55-04.318496.json,1791388336.5600789,1 +v1anneal_merge3_116k_120k,include_base_44_portuguese_stem,0,lm-eval,vllm,,acc,none,0.4,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c6c016ba77_2026-10-07T15-55-04.318496.json,1791388336.5600789,1 +v1anneal_merge3_116k_120k,include_base_44_serbian,0,lm-eval,vllm,yes,acc,none,0.6254545454545455,0.020546781944066415,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/50d6da4a40_2026-10-07T15-56-58.880480.json,1791388453.9692364,1 +v1anneal_merge3_116k_120k,include_base_44_serbian_arts_humanities,0,lm-eval,vllm,,acc,none,0.5846645367412141,0.027898161655867382,313,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/50d6da4a40_2026-10-07T15-56-58.880480.json,1791388453.9692364,1 +v1anneal_merge3_116k_120k,include_base_44_serbian_social_science,0,lm-eval,vllm,,acc,none,0.7058823529411765,0.03340951966159205,187,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/50d6da4a40_2026-10-07T15-56-58.880480.json,1791388453.9692364,1 +v1anneal_merge3_116k_120k,include_base_44_serbian_stem,0,lm-eval,vllm,,acc,none,0.58,0.07050835816716038,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/50d6da4a40_2026-10-07T15-56-58.880480.json,1791388453.9692364,1 +v1anneal_merge3_116k_120k,include_base_44_spanish,0,lm-eval,vllm,yes,acc,none,0.6418181818181818,0.02031552639536108,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3517435da_2026-10-07T15-42-32.739948.json,1791387590.555774,1 +v1anneal_merge3_116k_120k,include_base_44_spanish_arts_humanities,0,lm-eval,vllm,,acc,none,0.576,0.03131803437491622,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3517435da_2026-10-07T15-42-32.739948.json,1791387590.555774,1 +v1anneal_merge3_116k_120k,include_base_44_spanish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3517435da_2026-10-07T15-42-32.739948.json,1791387590.555774,1 +v1anneal_merge3_116k_120k,include_base_44_spanish_social_science,0,lm-eval,vllm,,acc,none,0.708,0.028814320402205634,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3517435da_2026-10-07T15-42-32.739948.json,1791387590.555774,1 +v1anneal_merge3_116k_120k,include_base_44_spanish_stem,0,lm-eval,vllm,,acc,none,0.72,0.0916515138991168,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c3517435da_2026-10-07T15-42-32.739948.json,1791387590.555774,1 +v1anneal_merge3_116k_120k,include_base_44_turkish,0,lm-eval,vllm,yes,acc,none,0.5583941605839416,0.0208981830587204,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b5370f3eda_2026-10-07T15-40-38.593212.json,1791387471.580908,1 +v1anneal_merge3_116k_120k,include_base_44_turkish_arts_humanities,0,lm-eval,vllm,,acc,none,0.5421686746987951,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b5370f3eda_2026-10-07T15-40-38.593212.json,1791387471.580908,1 +v1anneal_merge3_116k_120k,include_base_44_turkish_business_commerce,0,lm-eval,vllm,,acc,none,0.6867469879518072,0.036108050180310255,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b5370f3eda_2026-10-07T15-40-38.593212.json,1791387471.580908,1 +v1anneal_merge3_116k_120k,include_base_44_turkish_social_science,0,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b5370f3eda_2026-10-07T15-40-38.593212.json,1791387471.580908,1 +v1anneal_merge3_116k_120k,include_base_44_turkish_stem,0,lm-eval,vllm,,acc,none,0.38,0.06934092056863769,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b5370f3eda_2026-10-07T15-40-38.593212.json,1791387471.580908,1 +v1anneal_merge3_116k_120k,include_base_44_ukrainian,0,lm-eval,vllm,yes,acc,none,0.6181818181818182,0.020755227250063093,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b30d77095_2026-10-07T16-17-23.967914.json,1791389683.3019054,1 +v1anneal_merge3_116k_120k,include_base_44_ukrainian_arts_humanities,0,lm-eval,vllm,,acc,none,0.608,0.030938207620401222,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b30d77095_2026-10-07T16-17-23.967914.json,1791389683.3019054,1 +v1anneal_merge3_116k_120k,include_base_44_ukrainian_social_science,0,lm-eval,vllm,,acc,none,0.616,0.030821679117375447,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b30d77095_2026-10-07T16-17-23.967914.json,1791389683.3019054,1 +v1anneal_merge3_116k_120k,include_base_44_ukrainian_stem,0,lm-eval,vllm,,acc,none,0.68,0.06663945022680344,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b30d77095_2026-10-07T16-17-23.967914.json,1791389683.3019054,1 +v1anneal_merge3_116k_120k,jeopardy,10,lm-eval,vllm,,exact_match,strict-match,0.5243268776570619,0.010856692443144848,2117,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/30cf1bcaff_2026-10-07T16-21-53.548027.json,1791389927.053341,1 +v1anneal_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,acc,none,0.6947409276149815,0.006415903230922897,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5644741de3_2026-10-07T15-59-33.105465.json,1791388579.1583858,1 +v1anneal_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,perplexity,none,4.211839407522778,0.08635667676341202,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5644741de3_2026-10-07T15-59-33.105465.json,1791388579.1583858,1 +v1anneal_merge3_116k_120k,mbpp,3,lm-eval,vllm,,pass_at_1,none,0.588,0.022033677993740865,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9a5fd67ccb_2026-10-07T15-55-45.186374.json,1791388336.2602453,1 +v1anneal_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.708,0.028814320402205645,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83dc6c98c8_2026-10-07T16-19-55.590313.json,1791389818.9628062,1 +v1anneal_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,strict-match,0.764,0.026909337594953828,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83dc6c98c8_2026-10-07T16-19-55.590313.json,1791389818.9628062,1 +v1anneal_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.864,0.02172334261705206,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b43f754213_2026-10-07T16-13-42.262902.json,1791389451.552545,1 +v1anneal_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,strict-match,0.84,0.023232714782060657,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b43f754213_2026-10-07T16-13-42.262902.json,1791389451.552545,1 +v1anneal_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.776,0.026421361687347905,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ddb1949bb5_2026-10-07T15-57-08.763682.json,1791388459.1566935,1 +v1anneal_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,strict-match,0.732,0.028068762382526688,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ddb1949bb5_2026-10-07T15-57-08.763682.json,1791388459.1566935,1 +v1anneal_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.644,0.030343680657153215,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d089830e81_2026-10-07T16-01-13.044473.json,1791388699.100524,1 +v1anneal_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,strict-match,0.708,0.028814320402205655,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d089830e81_2026-10-07T16-01-13.044473.json,1791388699.100524,1 +v1anneal_merge3_116k_120k,mmlu,5,lm-eval,vllm,yes,acc,none,0.6865831078193989,0.003748631030087668,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_abstract_algebra,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_anatomy,5,lm-eval,vllm,,acc,none,0.5333333333333333,0.043097329010363616,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_business_ethics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6830188679245283,0.02863723563980094,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_college_computer_science,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_college_medicine,5,lm-eval,vllm,,acc,none,0.6705202312138728,0.03583901754736415,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_computer_security,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7489361702127659,0.02834696377716252,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_econometrics,5,lm-eval,vllm,,acc,none,0.5789473684210527,0.04644602091222323,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6689655172413793,0.03921545312467122,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6825396825396826,0.02397386199899207,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_biology,5,lm-eval,vllm,,acc,none,0.8580645161290322,0.019853003676559757,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6502463054187192,0.033554009049695604,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_geography,5,lm-eval,vllm,,acc,none,0.8232323232323232,0.027178752639044908,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9326424870466321,0.01808839383907894,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7589743589743589,0.021685546665333205,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5222222222222223,0.030455413985678415,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8109243697478992,0.025435119438105305,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_physics,5,lm-eval,vllm,,acc,none,0.5298013245033113,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8697247706422019,0.01443186285247314,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6481481481481481,0.032568505702936484,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8396624472573839,0.02388438092596563,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_human_aging,5,lm-eval,vllm,,acc,none,0.7174887892376681,0.030216831011508755,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_humanities,5,lm-eval,vllm,yes,acc,none,0.6320935175345377,0.00672254393476817,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_jurisprudence,5,lm-eval,vllm,,acc,none,0.8148148148148148,0.03755265865037181,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7791411042944786,0.032591773927421734,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_machine_learning,5,lm-eval,vllm,,acc,none,0.5446428571428571,0.04726835553719097,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_management,5,lm-eval,vllm,,acc,none,0.7961165048543689,0.0398913985953177,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_marketing,5,lm-eval,vllm,,acc,none,0.8846153846153846,0.0209301931851793,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_miscellaneous,5,lm-eval,vllm,,acc,none,0.7931034482758621,0.014485656041669067,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_moral_disputes,5,lm-eval,vllm,,acc,none,0.7572254335260116,0.02308365858698422,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_moral_scenarios,5,lm-eval,vllm,,acc,none,0.47374301675977654,0.016699427672784813,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_nutrition,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.026090162504279042,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_other,5,lm-eval,vllm,yes,acc,none,0.6993884776311554,0.007961127921664639,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_philosophy,5,lm-eval,vllm,,acc,none,0.7491961414790996,0.024619771956697113,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_prehistory,5,lm-eval,vllm,,acc,none,0.7438271604938271,0.02428853363772609,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_professional_accounting,5,lm-eval,vllm,,acc,none,0.4858156028368794,0.029815494483682023,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_professional_law,5,lm-eval,vllm,,acc,none,0.5136897001303781,0.012765448722610154,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_professional_medicine,5,lm-eval,vllm,,acc,none,0.6544117647058824,0.0288881931039887,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_professional_psychology,5,lm-eval,vllm,,acc,none,0.7238562091503268,0.018087276935663185,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_security_studies,5,lm-eval,vllm,,acc,none,0.7510204081632653,0.027682979522960276,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7916802079948001,0.007189204895027521,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_stem,5,lm-eval,vllm,yes,acc,none,0.6527117031398668,0.00820452505375643,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_virology,5,lm-eval,vllm,,acc,none,0.536144578313253,0.038823108508905954,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,mmlu_world_religions,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.03126781714663182,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5e1fea5dae_2026-10-07T15-45-34.641281.json,1791387587.1075265,1 +v1anneal_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc,none,0.9776240846216436,0.0029838279198856664,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69c15129e2_2026-10-07T15-57-04.120415.json,1791388458.1031518,1 +v1anneal_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc_norm,none,0.9747762408462164,0.0031634049861187304,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69c15129e2_2026-10-07T15-57-04.120415.json,1791388458.1031518,1 +v1anneal_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc,none,0.9759194395796847,0.003208391253078941,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/955781b8f4_2026-10-07T15-40-50.451034.json,1791387476.3900044,1 +v1anneal_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc_norm,none,0.9728546409807356,0.003401095421626418,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/955781b8f4_2026-10-07T15-40-50.451034.json,1791387476.3900044,1 +v1anneal_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc,none,0.9588815789473685,0.003044043962137247,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6fc8112fb3_2026-10-07T15-57-31.226125.json,1791388455.0031326,1 +v1anneal_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc_norm,none,0.9541823308270677,0.0032054012276831923,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6fc8112fb3_2026-10-07T15-57-31.226125.json,1791388455.0031326,1 +v1anneal_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b77a0ead15_2026-10-07T16-19-09.249453.json,1791389804.5737166,1 +v1anneal_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc_norm,none,0.98,0.02,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b77a0ead15_2026-10-07T16-19-09.249453.json,1791389804.5737166,1 +v1anneal_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc,none,0.9904264577893821,0.0020317344630233027,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/88569a1d30_2026-10-07T15-54-53.752300.json,1791388331.7041345,1 +v1anneal_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc_norm,none,0.9865100087032201,0.0024069999709337656,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/88569a1d30_2026-10-07T15-54-53.752300.json,1791388331.7041345,1 +v1anneal_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc,none,0.9936131386861314,0.0024073838689802887,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/64ca346fbf_2026-10-07T15-40-36.547934.json,1791387475.1571078,1 +v1anneal_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc_norm,none,0.9954379562043796,0.002036478192004258,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/64ca346fbf_2026-10-07T15-40-36.547934.json,1791387475.1571078,1 +v1anneal_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc,none,0.9883116883116884,0.0038757850932000515,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8e87b227f0_2026-10-07T15-54-39.930750.json,1791388328.913231,1 +v1anneal_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc_norm,none,0.9831168831168832,0.00464585574618289,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8e87b227f0_2026-10-07T15-54-39.930750.json,1791388328.913231,1 +v1anneal_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc,none,0.912621359223301,0.0055660061970424545,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/444acb4353_2026-10-07T15-36-29.473506.json,1791387222.8591664,1 +v1anneal_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc_norm,none,0.9207766990291262,0.00532352571250615,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/444acb4353_2026-10-07T15-36-29.473506.json,1791387222.8591664,1 +v1anneal_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc,none,0.9816849816849816,0.008130276209750445,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0e2ae205a6_2026-10-07T15-54-40.002314.json,1791388334.2871618,1 +v1anneal_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc_norm,none,0.6593406593406593,0.02873628536573398,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0e2ae205a6_2026-10-07T15-54-40.002314.json,1791388334.2871618,1 +v1anneal_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc,none,0.9501945525291828,0.004292028915578715,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c02247bc2c_2026-10-07T15-55-02.060726.json,1791388336.3563268,1 +v1anneal_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc_norm,none,0.9431906614785992,0.004566963705208012,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c02247bc2c_2026-10-07T15-55-02.060726.json,1791388336.3563268,1 +v1anneal_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc,none,0.9925431711145997,0.0017046582277653467,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f055662e55_2026-10-07T15-40-44.491051.json,1791387475.872323,1 +v1anneal_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc_norm,none,0.9878335949764521,0.0021722437610319687,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f055662e55_2026-10-07T15-40-44.491051.json,1791387475.872323,1 +v1anneal_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc,none,0.8928571428571429,0.05952380952380952,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83ddbfe66d_2026-10-07T15-56-35.675606.json,1791388459.5986178,1 +v1anneal_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc_norm,none,0.6785714285714286,0.08987898137227082,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/83ddbfe66d_2026-10-07T15-56-35.675606.json,1791388459.5986178,1 +v1anneal_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc,none,0.9707835325365206,0.006141382291691824,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/23c0e517ab_2026-10-07T15-54-56.120363.json,1791388332.4324036,1 +v1anneal_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc_norm,none,0.9601593625498008,0.007132238862645522,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/23c0e517ab_2026-10-07T15-54-56.120363.json,1791388332.4324036,1 +v1anneal_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc,none,0.9841752891052952,0.002177391050512167,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d77a39eb3c_2026-10-07T15-59-32.383341.json,1791388579.4932125,1 +v1anneal_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc_norm,none,0.9786975045648204,0.002519253055653842,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d77a39eb3c_2026-10-07T15-59-32.383341.json,1791388579.4932125,1 +v1anneal_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc,none,0.9893491124260355,0.0035334297490247305,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e0d6c39ef_2026-10-07T15-42-30.005891.json,1791387597.3131747,1 +v1anneal_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc_norm,none,0.98698224852071,0.0039016780971261656,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e0d6c39ef_2026-10-07T15-42-30.005891.json,1791387597.3131747,1 +v1anneal_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc,none,0.9785790789003928,0.002736138130836683,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/55eb17f160_2026-10-07T15-55-11.172414.json,1791388334.4949267,1 +v1anneal_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc_norm,none,0.9732238486254909,0.0030507135636062073,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/55eb17f160_2026-10-07T15-55-11.172414.json,1791388334.4949267,1 +v1anneal_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc,none,0.972324108036012,0.0029959911489586067,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d91dc702a7_2026-10-07T15-55-10.221556.json,1791388333.8366117,1 +v1anneal_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc_norm,none,0.9656552184061353,0.003326025779921726,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d91dc702a7_2026-10-07T15-55-10.221556.json,1791388333.8366117,1 +v1anneal_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc,none,0.9264705882352942,0.0183188558500897,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/79fa96dcec_2026-10-07T15-54-57.000991.json,1791388332.3205295,1 +v1anneal_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc_norm,none,0.8872549019607843,0.022198571039456782,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/79fa96dcec_2026-10-07T15-54-57.000991.json,1791388332.3205295,1 +v1anneal_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc,none,0.9538258575197889,0.003811895593963309,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93def1de37_2026-10-07T16-19-52.268135.json,1791389804.5967894,1 +v1anneal_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc_norm,none,0.95811345646438,0.003638754568401017,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/93def1de37_2026-10-07T16-19-52.268135.json,1791389804.5967894,1 +v1anneal_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc,none,0.9864406779661017,0.0033681976741896766,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/466124307c_2026-10-07T16-13-10.402306.json,1791389440.8703916,1 +v1anneal_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc_norm,none,0.9788135593220338,0.004193938779312167,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/466124307c_2026-10-07T16-13-10.402306.json,1791389440.8703916,1 +v1anneal_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f86a727448_2026-10-07T16-21-08.797746.json,1791389928.1675045,1 +v1anneal_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc_norm,none,0.9487179487179487,0.035781575124326184,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f86a727448_2026-10-07T16-21-08.797746.json,1791389928.1675045,1 +v1anneal_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc,none,0.9480909480909481,0.004595879019862996,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05ef151526_2026-10-07T16-15-17.462442.json,1791389556.9450727,1 +v1anneal_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc_norm,none,0.9313599313599313,0.005238050353853876,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05ef151526_2026-10-07T16-15-17.462442.json,1791389556.9450727,1 +v1anneal_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc,none,0.9654645476772616,0.003192717315517127,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b944832d0_2026-10-07T15-56-59.387932.json,1791388452.4203563,1 +v1anneal_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc_norm,none,0.9364303178484108,0.004266016009142298,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b944832d0_2026-10-07T15-56-59.387932.json,1791388452.4203563,1 +v1anneal_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc,none,0.9753937007874016,0.0028065765779403365,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5595794dbb_2026-10-07T15-40-53.538676.json,1791387478.5362816,1 +v1anneal_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc_norm,none,0.9734251968503937,0.002913735282093108,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5595794dbb_2026-10-07T15-40-53.538676.json,1791387478.5362816,1 +v1anneal_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc,none,0.9669260700389105,0.003944878420288837,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8e3a3867c2_2026-10-07T15-40-38.458704.json,1791387471.643146,1 +v1anneal_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc_norm,none,0.9620622568093385,0.0042143579649884105,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8e3a3867c2_2026-10-07T15-40-38.458704.json,1791387471.643146,1 +v1anneal_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc,none,0.9548854041013269,0.0032242171962903452,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c38d09a3c4_2026-10-07T15-36-36.766483.json,1791387224.0324056,1 +v1anneal_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc_norm,none,0.9558504221954162,0.003191158476005518,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c38d09a3c4_2026-10-07T15-36-36.766483.json,1791387224.0324056,1 +v1anneal_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc,none,0.9464644211465536,0.0033623078284970706,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0a3be8d365_2026-10-07T15-37-06.405594.json,1791387225.5083113,1 +v1anneal_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc_norm,none,0.9319652018737452,0.0037612263720751262,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0a3be8d365_2026-10-07T15-37-06.405594.json,1791387225.5083113,1 +v1anneal_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc,none,0.9748130657221566,0.0031090769207316768,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c217f6ceca_2026-10-07T15-59-14.832833.json,1791388580.6321778,1 +v1anneal_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc_norm,none,0.9787485242030697,0.002861628478432502,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c217f6ceca_2026-10-07T15-59-14.832833.json,1791388580.6321778,1 +v1anneal_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc,none,0.9835390946502057,0.008179278379751383,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/94c9cedcd5_2026-10-07T15-36-02.514158.json,1791387224.0153468,1 +v1anneal_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc_norm,none,0.9465020576131687,0.01446510656878504,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/94c9cedcd5_2026-10-07T15-36-02.514158.json,1791387224.0153468,1 +v1anneal_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc,none,0.9900497512437811,0.007018276606798947,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9c374ac29e_2026-10-07T15-56-31.525788.json,1791388455.3294506,1 +v1anneal_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc_norm,none,0.9850746268656716,0.00857397409931049,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9c374ac29e_2026-10-07T15-56-31.525788.json,1791388455.3294506,1 +v1anneal_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc,none,0.9190585533869116,0.006536686942345775,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc1ab86bcf_2026-10-07T16-17-25.069451.json,1791389695.3251014,1 +v1anneal_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc_norm,none,0.8536165327210103,0.008471845719471436,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc1ab86bcf_2026-10-07T16-17-25.069451.json,1791389695.3251014,1 +v1anneal_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc,none,0.9737609329446064,0.0030520206257348753,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a25c542ea_2026-10-07T15-42-46.925337.json,1791387595.0939777,1 +v1anneal_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc_norm,none,0.9639212827988338,0.0035606839310693868,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6a25c542ea_2026-10-07T15-42-46.925337.json,1791387595.0939777,1 +v1anneal_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc,none,0.314,0.020776701920308973,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2776292f5a_2026-10-07T15-57-11.505898.json,1791388463.7923748,1 +v1anneal_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc_norm,none,0.434,0.02218721580302901,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2776292f5a_2026-10-07T15-57-11.505898.json,1791388463.7923748,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,bleu,none,17.07847651882693,0.27161130323336014,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1a0237ac0f_2026-10-07T15-56-41.618066.json,1791388332.7997444,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,chrf,none,35.934451125197135,0.27341946636670555,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1a0237ac0f_2026-10-07T15-56-41.618066.json,1791388332.7997444,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,bleu,none,24.345067909885454,0.256909563738356,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d0a5fcbb3_2026-10-07T15-57-02.423897.json,1791388336.6550379,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,chrf,none,43.338355392456116,0.21909045254238926,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2d0a5fcbb3_2026-10-07T15-57-02.423897.json,1791388336.6550379,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,bleu,none,30.322170564922637,0.32236905601726024,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/159c97334a_2026-10-07T15-38-30.368604.json,1791387229.6408393,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,chrf,none,49.49725289261265,0.26509635617397564,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/159c97334a_2026-10-07T15-38-30.368604.json,1791387229.6408393,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,bleu,none,28.151367383033936,0.29920279982771136,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6581800de5_2026-10-07T16-17-30.206406.json,1791389566.9316716,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,chrf,none,48.53554007767949,0.25724252284231364,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6581800de5_2026-10-07T16-17-30.206406.json,1791389566.9316716,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,bleu,none,27.569175830871856,0.33531859760982363,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b70a9f765_2026-10-07T16-19-34.827555.json,1791389684.1896992,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,chrf,none,44.85554279987006,0.3636467527071527,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2b70a9f765_2026-10-07T16-19-34.827555.json,1791389684.1896992,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,bleu,none,13.584912050272687,0.2581272873666382,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f865e24a0b_2026-10-07T15-45-05.317225.json,1791387606.1305962,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,chrf,none,37.296224131425674,0.28705775211094414,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f865e24a0b_2026-10-07T15-45-05.317225.json,1791387606.1305962,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,bleu,none,16.948749475631104,0.3464653441033228,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/784956ff2c_2026-10-07T15-56-46.243741.json,1791388331.073529,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,chrf,none,36.67927526983436,0.31882416969392013,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/784956ff2c_2026-10-07T15-56-46.243741.json,1791388331.073529,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,bleu,none,29.69834572600658,0.31452298963027153,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc83b61bf7_2026-10-07T15-56-57.840164.json,1791388331.3397002,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,chrf,none,51.34281773938078,0.25055297563075346,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fc83b61bf7_2026-10-07T15-56-57.840164.json,1791388331.3397002,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,bleu,none,23.718930397417196,0.30649174238994475,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fd50a9ae9e_2026-10-07T15-42-44.754709.json,1791387466.867019,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,chrf,none,48.2320737035217,0.2944373305450647,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fd50a9ae9e_2026-10-07T15-42-44.754709.json,1791387466.867019,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,bleu,none,23.512779815264402,0.33590653856138175,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9815a50ee_2026-10-07T15-59-28.028168.json,1791388461.4494736,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,chrf,none,45.451884073090135,0.3095019418913133,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a9815a50ee_2026-10-07T15-59-28.028168.json,1791388461.4494736,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,bleu,none,28.469910259007268,0.3520595365928229,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/914b94d213_2026-10-07T16-19-47.566465.json,1791389690.7631137,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,chrf,none,51.298561859386325,0.2925354751428944,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/914b94d213_2026-10-07T16-19-47.566465.json,1791389690.7631137,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,bleu,none,21.404153236880877,0.36592045641072907,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dcf429c88f_2026-10-07T16-01-13.945743.json,1791388589.0521417,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,chrf,none,44.214918579137525,0.28509953845003083,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dcf429c88f_2026-10-07T16-01-13.945743.json,1791388589.0521417,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,bleu,none,16.09409894703385,0.33485767588568466,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0873f63749_2026-10-07T15-38-33.663730.json,1791387228.3199322,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,chrf,none,43.17073372787423,0.2929143252449726,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0873f63749_2026-10-07T15-38-33.663730.json,1791387228.3199322,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,bleu,none,16.70675813659812,0.23991447964135382,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dd5358e422_2026-10-07T16-17-34.476664.json,1791389566.076115,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,chrf,none,43.7039933326162,0.2512476229554818,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dd5358e422_2026-10-07T16-17-34.476664.json,1791389566.076115,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,bleu,none,24.431719718615266,0.3363382235537036,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aee425a754_2026-10-07T15-38-34.138426.json,1791387223.0117407,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,chrf,none,50.12685700592391,0.31777871323314094,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/aee425a754_2026-10-07T15-38-34.138426.json,1791387223.0117407,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,bleu,none,16.394565994407998,0.2922096355419144,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1af0d4ad7c_2026-10-07T16-03-21.126168.json,1791388699.8209126,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,chrf,none,36.62528963951921,0.2778580134700955,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1af0d4ad7c_2026-10-07T16-03-21.126168.json,1791388699.8209126,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,bleu,none,28.226252957293656,0.3488015349040802,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e2140743f7_2026-10-07T15-57-02.356328.json,1791388334.9279811,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,chrf,none,51.03653236750593,0.24745711406434132,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e2140743f7_2026-10-07T15-57-02.356328.json,1791388334.9279811,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,bleu,none,17.77047961036097,0.3046061296708401,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d64a6922cd_2026-10-07T15-59-16.940568.json,1791388458.2678218,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,chrf,none,41.87037868379454,0.24802235700774267,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d64a6922cd_2026-10-07T15-59-16.940568.json,1791388458.2678218,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,bleu,none,20.511494957034174,0.32691626837461146,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0f8d1138bd_2026-10-07T16-01-14.860677.json,1791388576.9871929,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,chrf,none,43.88568743752578,0.2372663959676855,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0f8d1138bd_2026-10-07T16-01-14.860677.json,1791388576.9871929,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,bleu,none,20.101668491663066,0.2730121684513966,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7654018008_2026-10-07T15-59-01.457575.json,1791388453.5285294,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,chrf,none,46.030548647669804,0.26896634916991663,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7654018008_2026-10-07T15-59-01.457575.json,1791388453.5285294,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,bleu,none,31.571157844755287,0.3033743352721041,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3412320ca1_2026-10-07T15-42-24.137401.json,1791387467.0787287,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,chrf,none,54.70430768101156,0.29176859231918123,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3412320ca1_2026-10-07T15-42-24.137401.json,1791387467.0787287,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,bleu,none,20.253712428659096,0.3090945405981376,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8e2f2dfe30_2026-10-07T15-42-38.033860.json,1791387474.9712386,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,chrf,none,44.62587603723236,0.27394678744459705,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8e2f2dfe30_2026-10-07T15-42-38.033860.json,1791387474.9712386,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,bleu,none,24.464653868713555,0.27838424109437104,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f96387b9c_2026-10-07T16-15-30.086748.json,1791389436.5904129,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,chrf,none,50.68362468131766,0.27674573681099923,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f96387b9c_2026-10-07T16-15-30.086748.json,1791389436.5904129,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,bleu,none,26.18218408488857,0.3501434575421705,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f6778289a0_2026-10-07T16-01-27.338627.json,1791388586.933523,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,chrf,none,50.788672392749866,0.2785769152897399,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f6778289a0_2026-10-07T16-01-27.338627.json,1791388586.933523,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,bleu,none,22.512480930947625,0.4109963346157042,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8b0cf6c7d7_2026-10-07T16-01-22.105617.json,1791388580.8577757,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,chrf,none,42.40592241347534,0.34050629083187783,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8b0cf6c7d7_2026-10-07T16-01-22.105617.json,1791388580.8577757,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,bleu,none,14.838129998170324,0.257130492258135,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f682f535d7_2026-10-07T16-15-24.067881.json,1791389449.1782765,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,chrf,none,40.51885733262195,0.25437178285808226,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f682f535d7_2026-10-07T16-15-24.067881.json,1791389449.1782765,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,bleu,none,15.029951487334971,0.3164509014769671,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c9fb629eee_2026-10-07T15-42-40.098072.json,1791387476.3805928,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,chrf,none,30.588665227103455,0.4472163834720583,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c9fb629eee_2026-10-07T15-42-40.098072.json,1791387476.3805928,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,bleu,none,34.56835616966964,0.3373655343695058,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ae5474eaf1_2026-10-07T16-21-33.414113.json,1791389809.0273814,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,chrf,none,54.5892670777547,0.27803844037355796,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ae5474eaf1_2026-10-07T16-21-33.414113.json,1791389809.0273814,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,bleu,none,19.745783189269034,0.349835709127147,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/908ba5d622_2026-10-07T16-01-14.265858.json,1791388575.7933567,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,chrf,none,47.50202567985903,0.30083018928355276,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/908ba5d622_2026-10-07T16-01-14.265858.json,1791388575.7933567,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,bleu,none,16.816061540351484,0.271208559824268,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60dfc47034_2026-10-07T16-03-15.579510.json,1791388702.4612882,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,chrf,none,38.621870085286794,0.27756160450375655,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60dfc47034_2026-10-07T16-03-15.579510.json,1791388702.4612882,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,bleu,none,31.80898844998465,0.32649048729486696,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ed2754e95_2026-10-07T15-44-34.928697.json,1791387589.748967,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,chrf,none,50.715038700126236,0.2716988130865023,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ed2754e95_2026-10-07T15-44-34.928697.json,1791387589.748967,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,bleu,none,28.50633175455742,0.3383885900049056,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d839cf72fc_2026-10-07T15-57-04.380750.json,1791388336.2289205,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,chrf,none,47.353379299227804,0.25621795850768325,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d839cf72fc_2026-10-07T15-57-04.380750.json,1791388336.2289205,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,bleu,none,23.496608549202605,0.3159010383202772,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/237894455c_2026-10-07T15-44-36.627937.json,1791387594.249102,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,chrf,none,43.41170737001714,0.2519486309627017,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/237894455c_2026-10-07T15-44-36.627937.json,1791387594.249102,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,bleu,none,19.67237266593384,0.2702891476067352,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3261ca99f4_2026-10-07T16-21-27.430778.json,1791389810.598253,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,chrf,none,39.360105530135606,0.23913723882013976,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3261ca99f4_2026-10-07T16-21-27.430778.json,1791389810.598253,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,bleu,none,25.03361459533622,0.3998081571170966,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/acf21b743b_2026-10-07T16-00-58.061932.json,1791388576.8401766,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,chrf,none,43.710588388362694,0.39317252809773334,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/acf21b743b_2026-10-07T16-00-58.061932.json,1791388576.8401766,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,bleu,none,23.187289016307144,0.3082301078984989,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/336b07eef4_2026-10-07T15-42-34.016628.json,1791387470.8923979,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,chrf,none,42.01065432079184,0.2563225888479921,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/336b07eef4_2026-10-07T15-42-34.016628.json,1791387470.8923979,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,bleu,none,31.9984028230862,0.28288191498560206,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/08614d9fe9_2026-10-07T15-38-33.545357.json,1791387223.6648915,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,chrf,none,50.13525770493915,0.2479412995615638,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/08614d9fe9_2026-10-07T15-38-33.545357.json,1791387223.6648915,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,bleu,none,25.993537634369414,0.3265193125729666,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bd6e0575dc_2026-10-07T15-42-39.589811.json,1791387469.2723293,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,chrf,none,43.87808003918649,0.2661671490562911,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bd6e0575dc_2026-10-07T15-42-39.589811.json,1791387469.2723293,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,bleu,none,27.58361006805534,0.32856108756901115,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb7f668c89_2026-10-07T16-21-39.874955.json,1791389809.0082157,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,chrf,none,45.85515241084314,0.2979540007134005,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bb7f668c89_2026-10-07T16-21-39.874955.json,1791389809.0082157,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,bleu,none,23.498473623159956,0.2923505108186442,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7db4f458b8_2026-10-07T16-03-08.068089.json,1791388704.510219,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,chrf,none,42.70639149738466,0.24275041778702788,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/7db4f458b8_2026-10-07T16-03-08.068089.json,1791388704.510219,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,bleu,none,32.111334358695125,0.3197736223353635,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69bb9cfd34_2026-10-07T15-58-55.004982.json,1791388453.865912,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,chrf,none,50.73673199346208,0.26960814748597783,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/69bb9cfd34_2026-10-07T15-58-55.004982.json,1791388453.865912,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,bleu,none,26.51581300507491,0.31477131947855946,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef077d61f6_2026-10-07T16-21-40.323887.json,1791389810.6385703,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,chrf,none,45.70389921617313,0.2768920001882899,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef077d61f6_2026-10-07T16-21-40.323887.json,1791389810.6385703,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,bleu,none,34.632189810925226,0.3395275920293861,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a539dd4ccb_2026-10-07T15-44-40.614925.json,1791387588.2287002,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,chrf,none,53.025803490197,0.2749609513385678,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a539dd4ccb_2026-10-07T15-44-40.614925.json,1791387588.2287002,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,bleu,none,33.76749924604762,0.3697468237709741,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/47b0845bc9_2026-10-07T16-19-32.080572.json,1791389683.1977248,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,chrf,none,51.64019290625189,0.2791148814835389,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/47b0845bc9_2026-10-07T16-19-32.080572.json,1791389683.1977248,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,bleu,none,30.821236944669575,0.33067940891473185,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a420cc86de_2026-10-07T16-19-32.491428.json,1791389685.7160406,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,chrf,none,48.56859109021763,0.26982389420175257,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a420cc86de_2026-10-07T16-19-32.491428.json,1791389685.7160406,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,bleu,none,20.633842756930935,0.2657625532606596,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0176c10789_2026-10-07T15-56-37.137413.json,1791388327.2390082,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,chrf,none,40.21293256468388,0.25369744286262863,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0176c10789_2026-10-07T15-56-37.137413.json,1791388327.2390082,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,bleu,none,29.402834362729283,0.34844298188028683,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3629359ed1_2026-10-07T16-03-20.120045.json,1791388707.0873902,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,chrf,none,49.649460595849845,0.3043762875694932,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3629359ed1_2026-10-07T16-03-20.120045.json,1791388707.0873902,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,bleu,none,37.8178204685548,0.33368269019622915,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/76afca3075_2026-10-07T15-38-23.879409.json,1791387221.9883432,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,chrf,none,54.792145785141734,0.2791124757507507,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/76afca3075_2026-10-07T15-38-23.879409.json,1791387221.9883432,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,bleu,none,27.699907119419198,0.30966778770374775,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/685d5da94e_2026-10-07T15-43-08.905676.json,1791387473.435749,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,chrf,none,47.188363083562784,0.3068814630834909,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/685d5da94e_2026-10-07T15-43-08.905676.json,1791387473.435749,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,bleu,none,24.36117919666313,0.3126002180898246,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/961f4f2ae9_2026-10-07T15-57-06.209081.json,1791388330.1265235,1 +v1anneal_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,chrf,none,43.31405571921002,0.26096474906066597,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/961f4f2ae9_2026-10-07T15-57-06.209081.json,1791388330.1265235,1 +v1anneal_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc,none,0.7965179542981502,0.009393041784049939,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ea1a189db6_2026-10-07T15-59-16.247286.json,1791388577.815277,1 +v1anneal_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc_norm,none,0.8101196953210011,0.009150819250948662,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ea1a189db6_2026-10-07T15-59-16.247286.json,1791388577.815277,1 +v1anneal_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc,none,0.8144722524483133,0.009069597302603977,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/978250001f_2026-10-07T16-13-51.183747.json,1791389444.1158419,1 +v1anneal_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc_norm,none,0.823177366702938,0.008901456201658588,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/978250001f_2026-10-07T16-13-51.183747.json,1791389444.1158419,1 +v1anneal_merge3_116k_120k,polymath_de_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9bd3b0181e_2026-10-07T16-13-46.334185.json,1791389437.3675456,1 +v1anneal_merge3_116k_120k,polymath_de_low,0,lm-eval,vllm,,exact_match,none,0.536,0.044784790044777915,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9e246e4e32_2026-10-07T15-57-33.505651.json,1791388464.2328014,1 +v1anneal_merge3_116k_120k,polymath_de_medium,0,lm-eval,vllm,,exact_match,none,0.08,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/796866c333_2026-10-07T15-36-54.270434.json,1791387228.83247,1 +v1anneal_merge3_116k_120k,polymath_de_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9ea761ab3d_2026-10-07T15-59-26.858422.json,1791388576.9250658,1 +v1anneal_merge3_116k_120k,polymath_en_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/45fb714731_2026-10-07T15-43-06.918882.json,1791387599.7595541,1 +v1anneal_merge3_116k_120k,polymath_en_low,0,lm-eval,vllm,,exact_match,none,0.512,0.044888392062263534,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ed456a95a_2026-10-07T16-14-03.535999.json,1791389444.5136178,1 +v1anneal_merge3_116k_120k,polymath_en_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/64adf83874_2026-10-07T15-57-31.815110.json,1791388457.7255971,1 +v1anneal_merge3_116k_120k,polymath_en_top,0,lm-eval,vllm,,exact_match,none,0.056,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0910b1fc05_2026-10-07T15-43-01.386199.json,1791387592.1943903,1 +v1anneal_merge3_116k_120k,polymath_es_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a562039fc6_2026-10-07T15-41-12.708442.json,1791387481.2172465,1 +v1anneal_merge3_116k_120k,polymath_es_low,0,lm-eval,vllm,,exact_match,none,0.456,0.04472712967576008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/29221b355d_2026-10-07T16-16-05.673927.json,1791389563.9078116,1 +v1anneal_merge3_116k_120k,polymath_es_medium,0,lm-eval,vllm,,exact_match,none,0.144,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/56d4f5a4a3_2026-10-07T16-15-59.994754.json,1791389566.3263738,1 +v1anneal_merge3_116k_120k,polymath_es_top,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4cc46709dd_2026-10-07T16-19-55.851140.json,1791389808.700644,1 +v1anneal_merge3_116k_120k,polymath_fr_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b877208cdc_2026-10-07T16-13-46.381243.json,1791389443.2368903,1 +v1anneal_merge3_116k_120k,polymath_fr_low,0,lm-eval,vllm,,exact_match,none,0.544,0.04472712967576008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e9e9eb0822_2026-10-07T16-22-04.566673.json,1791389935.4711735,1 +v1anneal_merge3_116k_120k,polymath_fr_medium,0,lm-eval,vllm,,exact_match,none,0.128,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/56a6d5fe63_2026-10-07T16-19-53.186720.json,1791389805.132884,1 +v1anneal_merge3_116k_120k,polymath_fr_top,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4324949110_2026-10-07T15-40-57.308425.json,1791387467.4128683,1 +v1anneal_merge3_116k_120k,polymath_it_high,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c5a0fe3ac2_2026-10-07T15-40-50.644697.json,1791387467.5413797,1 +v1anneal_merge3_116k_120k,polymath_it_low,0,lm-eval,vllm,,exact_match,none,0.584,0.044263142753894154,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/462cdf20e6_2026-10-07T15-43-06.525104.json,1791387598.297971,1 +v1anneal_merge3_116k_120k,polymath_it_medium,0,lm-eval,vllm,,exact_match,none,0.104,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ba703213ea_2026-10-07T15-59-18.502329.json,1791388576.2857742,1 +v1anneal_merge3_116k_120k,polymath_it_top,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/05a4cdcb3c_2026-10-07T15-59-29.238743.json,1791388577.5206556,1 +v1anneal_merge3_116k_120k,polymath_pt_high,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/752123c5bf_2026-10-07T15-55-34.671571.json,1791388341.5743349,1 +v1anneal_merge3_116k_120k,polymath_pt_low,0,lm-eval,vllm,,exact_match,none,0.632,0.043308346807812995,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d9b9a62552_2026-10-07T16-21-49.631830.json,1791389926.414652,1 +v1anneal_merge3_116k_120k,polymath_pt_medium,0,lm-eval,vllm,,exact_match,none,0.12,0.029182407426835203,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/32953370b6_2026-10-07T15-55-19.035141.json,1791388333.1180334,1 +v1anneal_merge3_116k_120k,polymath_pt_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f0f442b286_2026-10-07T15-41-06.806962.json,1791387472.756752,1 +v1anneal_merge3_116k_120k,sib200_als_Latn,0,lm-eval,vllm,,acc,none,0.2647058823529412,0.030964517926923372,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4bb098ef1a_2026-10-07T15-55-05.092898.json,1791388338.1324391,1 +v1anneal_merge3_116k_120k,sib200_bos_Latn,0,lm-eval,vllm,,acc,none,0.30392156862745096,0.03228210387037892,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/afce2ae260_2026-10-07T16-21-32.399092.json,1791389927.0663774,1 +v1anneal_merge3_116k_120k,sib200_bul_Cyrl,0,lm-eval,vllm,,acc,none,0.25980392156862747,0.030778554678693247,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d1cffd6b78_2026-10-07T15-40-34.669932.json,1791387468.8738308,1 +v1anneal_merge3_116k_120k,sib200_cat_Latn,0,lm-eval,vllm,,acc,none,0.3137254901960784,0.03256685484460391,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/dfc5e1c610_2026-10-07T15-36-25.203217.json,1791387223.819854,1 +v1anneal_merge3_116k_120k,sib200_ces_Latn,0,lm-eval,vllm,,acc,none,0.30392156862745096,0.03228210387037892,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ef3807d356_2026-10-07T15-40-31.696930.json,1791387470.16386,1 +v1anneal_merge3_116k_120k,sib200_dan_Latn,0,lm-eval,vllm,,acc,none,0.3284313725490196,0.03296245110172227,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/e0ea2bcdbf_2026-10-07T15-56-59.567773.json,1791388456.204011,1 +v1anneal_merge3_116k_120k,sib200_deu_Latn,0,lm-eval,vllm,,acc,none,0.29411764705882354,0.031980016601150726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/67df7baae3_2026-10-07T16-01-05.906922.json,1791388705.1906717,1 +v1anneal_merge3_116k_120k,sib200_ell_Grek,0,lm-eval,vllm,,acc,none,0.28431372549019607,0.03166009679399808,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/b08864de51_2026-10-07T15-36-29.695003.json,1791387226.6009953,1 +v1anneal_merge3_116k_120k,sib200_eng_Latn,0,lm-eval,vllm,,acc,none,0.3088235294117647,0.03242661719827215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3fddfc75df_2026-10-07T15-57-03.426999.json,1791388458.584443,1 +v1anneal_merge3_116k_120k,sib200_est_Latn,0,lm-eval,vllm,,acc,none,0.23039215686274508,0.029554292605695046,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1a44320dca_2026-10-07T15-57-04.735466.json,1791388459.5030725,1 +v1anneal_merge3_116k_120k,sib200_eus_Latn,0,lm-eval,vllm,,acc,none,0.3137254901960784,0.03256685484460391,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3b15ae9b3a_2026-10-07T15-36-23.367761.json,1791387224.2679493,1 +v1anneal_merge3_116k_120k,sib200_fin_Latn,0,lm-eval,vllm,,acc,none,0.28921568627450983,0.031822318676475524,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/13f70f8011_2026-10-07T16-15-13.840052.json,1791389556.932498,1 +v1anneal_merge3_116k_120k,sib200_fra_Latn,0,lm-eval,vllm,,acc,none,0.3137254901960784,0.03256685484460391,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/89a6869fde_2026-10-07T15-36-27.588170.json,1791387225.421699,1 +v1anneal_merge3_116k_120k,sib200_gle_Latn,0,lm-eval,vllm,,acc,none,0.2647058823529412,0.030964517926923372,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/20f8dde10f_2026-10-07T15-59-14.648501.json,1791388584.5991178,1 +v1anneal_merge3_116k_120k,sib200_glg_Latn,0,lm-eval,vllm,,acc,none,0.3088235294117647,0.03242661719827215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cd640aa590_2026-10-07T15-40-41.552721.json,1791387480.4889462,1 +v1anneal_merge3_116k_120k,sib200_hrv_Latn,0,lm-eval,vllm,,acc,none,0.27941176470588236,0.031493281045079584,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/0761c069f3_2026-10-07T15-40-33.259308.json,1791387470.875795,1 +v1anneal_merge3_116k_120k,sib200_hun_Latn,0,lm-eval,vllm,,acc,none,0.27941176470588236,0.031493281045079584,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bab5281b79_2026-10-07T16-19-18.484535.json,1791389807.38113,1 +v1anneal_merge3_116k_120k,sib200_isl_Latn,0,lm-eval,vllm,,acc,none,0.3235294117647059,0.032834720561085606,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/2138ba3e22_2026-10-07T15-57-07.149765.json,1791388462.3221133,1 +v1anneal_merge3_116k_120k,sib200_ita_Latn,0,lm-eval,vllm,,acc,none,0.31862745098039214,0.032702871814820796,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/41330dd8e4_2026-10-07T15-57-08.439348.json,1791388463.8335211,1 +v1anneal_merge3_116k_120k,sib200_kat_Geor,0,lm-eval,vllm,,acc,none,0.37254901960784315,0.03393388584958406,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/c235c4a246_2026-10-07T16-13-33.639176.json,1791389444.511343,1 +v1anneal_merge3_116k_120k,sib200_lit_Latn,0,lm-eval,vllm,,acc,none,0.3235294117647059,0.032834720561085606,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/326122a4bf_2026-10-07T15-54-57.484804.json,1791388334.984349,1 +v1anneal_merge3_116k_120k,sib200_lvs_Latn,0,lm-eval,vllm,,acc,none,0.28921568627450983,0.031822318676475524,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4097532a73_2026-10-07T15-54-51.556271.json,1791388332.245957,1 +v1anneal_merge3_116k_120k,sib200_mkd_Cyrl,0,lm-eval,vllm,,acc,none,0.27941176470588236,0.031493281045079584,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/15d30dffb1_2026-10-07T15-59-00.855674.json,1791388577.6455722,1 +v1anneal_merge3_116k_120k,sib200_mlt_Latn,0,lm-eval,vllm,,acc,none,0.25980392156862747,0.030778554678693247,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/60c0abf5be_2026-10-07T15-36-37.603598.json,1791387228.9089556,1 +v1anneal_merge3_116k_120k,sib200_nld_Latn,0,lm-eval,vllm,,acc,none,0.28921568627450983,0.031822318676475524,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/fbde980ba6_2026-10-07T15-40-39.035857.json,1791387475.0084693,1 +v1anneal_merge3_116k_120k,sib200_nob_Latn,0,lm-eval,vllm,,acc,none,0.36764705882352944,0.0338413204567412,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/040764bb27_2026-10-07T16-13-26.535141.json,1791389438.1080167,1 +v1anneal_merge3_116k_120k,sib200_pol_Latn,0,lm-eval,vllm,,acc,none,0.31862745098039214,0.032702871814820796,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/63410660f2_2026-10-07T15-36-39.291523.json,1791387227.154728,1 +v1anneal_merge3_116k_120k,sib200_por_Latn,0,lm-eval,vllm,,acc,none,0.3235294117647059,0.032834720561085606,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/55416b8c8d_2026-10-07T16-17-17.548208.json,1791389672.6129272,1 +v1anneal_merge3_116k_120k,sib200_ron_Latn,0,lm-eval,vllm,,acc,none,0.31862745098039214,0.032702871814820796,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1f67d73ec6_2026-10-07T15-40-24.046736.json,1791387466.1755004,1 +v1anneal_merge3_116k_120k,sib200_slk_Latn,0,lm-eval,vllm,,acc,none,0.28431372549019607,0.03166009679399808,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/9d00b2932d_2026-10-07T15-54-59.003350.json,1791388336.926857,1 +v1anneal_merge3_116k_120k,sib200_slv_Latn,0,lm-eval,vllm,,acc,none,0.3284313725490196,0.03296245110172227,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/75d247869c_2026-10-07T15-36-43.532930.json,1791387226.9790137,1 +v1anneal_merge3_116k_120k,sib200_spa_Latn,0,lm-eval,vllm,,acc,none,0.27450980392156865,0.03132179803083291,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/cc97b36607_2026-10-07T16-01-10.191577.json,1791388705.281813,1 +v1anneal_merge3_116k_120k,sib200_srp_Cyrl,0,lm-eval,vllm,,acc,none,0.28431372549019607,0.03166009679399808,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/230ec621d9_2026-10-07T15-36-23.082012.json,1791387221.8769143,1 +v1anneal_merge3_116k_120k,sib200_swe_Latn,0,lm-eval,vllm,,acc,none,0.35784313725490197,0.033644872860883,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/4ac2d839c9_2026-10-07T15-42-30.146645.json,1791387588.498207,1 +v1anneal_merge3_116k_120k,sib200_tur_Latn,0,lm-eval,vllm,,acc,none,0.3235294117647059,0.032834720561085606,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/54f86f595a_2026-10-07T15-40-39.813568.json,1791387467.8363163,1 +v1anneal_merge3_116k_120k,sib200_ukr_Cyrl,0,lm-eval,vllm,,acc,none,0.3088235294117647,0.03242661719827215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/6e0a133d7a_2026-10-07T15-55-02.554873.json,1791388338.302358,1 +v1anneal_merge3_116k_120k,social_iqa,0,lm-eval,vllm,,acc,none,0.47236438075742065,0.011296775603774168,1954,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/bfd49bd26f_2026-10-07T15-36-34.570476.json,1791387221.8173194,1 +v1anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_exact,none,76.51821862348179,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb1a6d7a3_2026-10-07T16-30-37.549704.json,1791388708.925542,1 +v1anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_f1,none,83.08380921356103,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb1a6d7a3_2026-10-07T16-30-37.549704.json,1791388708.925542,1 +v1anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_exact,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb1a6d7a3_2026-10-07T16-30-37.549704.json,1791388708.925542,1 +v1anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_f1,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb1a6d7a3_2026-10-07T16-30-37.549704.json,1791388708.925542,1 +v1anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_exact,none,61.10502821527836,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb1a6d7a3_2026-10-07T16-30-37.549704.json,1791388708.925542,1 +v1anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_f1,none,63.47646759844359,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb1a6d7a3_2026-10-07T16-30-37.549704.json,1791388708.925542,1 +v1anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,exact,none,38.20432915017266,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb1a6d7a3_2026-10-07T16-30-37.549704.json,1791388708.925542,1 +v1anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,f1,none,41.48242407293774,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/8bb1a6d7a3_2026-10-07T16-30-37.549704.json,1791388708.925542,1 +v1anneal_merge3_116k_120k,winogrande,0,lm-eval,vllm,,acc,none,0.7119179163378059,0.012727884724248026,1267,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/f8781b6832_2026-10-07T15-55-04.273815.json,1791388341.564884,1 +v1anneal_merge3_116k_120k,wsc273,0,lm-eval,vllm,,acc,none,0.8388278388278388,0.02229446116547852,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/3f74b5709d_2026-10-07T15-55-04.594248.json,1791388332.4531255,1 +v1anneal_merge3_116k_120k,xcopa:et,0,lighteval,hf/accelerate,,acc,none,0.608,0.021854684955611263,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/3932b35e70/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T15-59-38.935811.json,1791388779.0177233,1 +v1anneal_merge3_116k_120k,xcopa:it,0,lighteval,hf/accelerate,,acc,none,0.638,0.021513662527582397,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/67987992cc/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T16-01-43.929599.json,1791388904.0161211,1 +v1anneal_merge3_116k_120k,xcopa:tr,0,lighteval,hf/accelerate,,acc,none,0.652,0.021323728632807498,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-03/results/7a6d2869a9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v1anneal_merge3_116k_120k/results_2026-10-07T15-59-33.119938.json,1791388773.2037084,1 +v1anneal_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc,none,0.477,0.015802554246726087,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b2d54ac06_2026-10-07T15-55-02.891698.json,1791388334.9416177,1 +v1anneal_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc_norm,none,0.465,0.015780495050030086,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/1b2d54ac06_2026-10-07T15-55-02.891698.json,1791388334.9416177,1 +v1anneal_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc,none,0.624,0.0153251055088981,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/28e36f6c84_2026-10-07T15-59-05.200958.json,1791388584.6426759,1 +v1anneal_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc_norm,none,0.635,0.015231776226264848,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/28e36f6c84_2026-10-07T15-59-05.200958.json,1791388584.6426759,1 +v1anneal_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc,none,0.47,0.015790799515836725,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d2aab4f397_2026-10-07T15-40-37.800850.json,1791387471.6131244,1 +v1anneal_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc_norm,none,0.431,0.01566794448817344,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d2aab4f397_2026-10-07T15-40-37.800850.json,1791387471.6131244,1 +v1anneal_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc,none,0.482,0.01580904569940659,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a337e93c76_2026-10-07T16-13-28.225597.json,1791389442.9157279,1 +v1anneal_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc_norm,none,0.434,0.015680876566375044,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/a337e93c76_2026-10-07T16-13-28.225597.json,1791389442.9157279,1 +v1anneal_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc,none,0.454,0.01575221038877186,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d344b56d5a_2026-10-07T15-59-02.336487.json,1791388577.0887856,1 +v1anneal_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc_norm,none,0.449,0.015736792768752044,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d344b56d5a_2026-10-07T15-59-02.336487.json,1791388577.0887856,1 +v1anneal_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc,none,0.385,0.015395194445410945,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d892b8e188_2026-10-07T15-54-58.963035.json,1791388334.0438516,1 +v1anneal_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc_norm,none,0.379,0.015349091002225332,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/d892b8e188_2026-10-07T15-54-58.963035.json,1791388334.0438516,1 +v1anneal_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.457,0.0157606915901365,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5200fc1f27_2026-10-07T16-21-45.537733.json,1791389932.7773302,1 +v1anneal_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.436,0.015689173023144022,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/5200fc1f27_2026-10-07T16-21-45.537733.json,1791389932.7773302,1 +v1anneal_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.439,0.015701131345400736,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ccd23244ee_2026-10-07T15-40-35.121528.json,1791387467.3123143,1 +v1anneal_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.409,0.015555094373257944,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/vllm/2026-10-07-17-31-01/results/ccd23244ee_2026-10-07T15-40-35.121528.json,1791387467.3123143,1 +v1anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@1,all,0.19375,0.057785554065187344,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b90c789e0a_2026-10-08T23-20-54.567614.json,1791500509.4091241,1 +v1anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@16,all,0.34969130124729797,0.0868545894636443,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b90c789e0a_2026-10-08T23-20-54.567614.json,1791500509.4091241,1 +v1anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@32,all,0.36666666666666664,0.08948554539839963,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b90c789e0a_2026-10-08T23-20-54.567614.json,1791500509.4091241,1 +v1anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@4,all,0.30382183908045973,0.0795014866010323,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b90c789e0a_2026-10-08T23-20-54.567614.json,1791500509.4091241,1 +v1anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,think_closed,all,0.13645833333333332,0.04915968012410388,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b90c789e0a_2026-10-08T23-20-54.567614.json,1791500509.4091241,1 +v1anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@1,all,0.20833333333333334,0.06736345633236276,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d9c73e16be_2026-10-08T23-20-54.456384.json,1791500512.0053685,1 +v1anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@16,all,0.29898240843735835,0.08481066588198795,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d9c73e16be_2026-10-08T23-20-54.456384.json,1791500512.0053685,1 +v1anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@32,all,0.3,0.08509629433967632,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d9c73e16be_2026-10-08T23-20-54.456384.json,1791500512.0053685,1 +v1anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@4,all,0.2682823507601038,0.07841734377286129,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d9c73e16be_2026-10-08T23-20-54.456384.json,1791500512.0053685,1 +v1anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,think_closed,all,0.17708333333333334,0.06192866253436303,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/d9c73e16be_2026-10-08T23-20-54.456384.json,1791500512.0053685,1 +v1anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@1,all,0.546875,0.06396519736824842,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c51d6e2c79_2026-10-08T23-21-42.890094.json,1791500506.4945772,1 +v1anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@16,all,0.8528884602690165,0.053214139409963494,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c51d6e2c79_2026-10-08T23-21-42.890094.json,1791500506.4945772,1 +v1anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@32,all,0.875,0.05295740910852021,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c51d6e2c79_2026-10-08T23-21-42.890094.json,1791500506.4945772,1 +v1anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@4,all,0.727639043381535,0.05741550472127797,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c51d6e2c79_2026-10-08T23-21-42.890094.json,1791500506.4945772,1 +v1anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,think_closed,all,0.47734375,0.06866606454772807,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c51d6e2c79_2026-10-08T23-21-42.890094.json,1791500506.4945772,1 +v1anneal_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,pass@1,all,0.37626262626262624,0.030048259028969702,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/be98031c58_2026-10-08T23-28-59.881592.json,1791500509.8306046,1 +v1anneal_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,think_closed,all,0.255050505050505,0.027903348716289803,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/be98031c58_2026-10-08T23-28-59.881592.json,1791500509.8306046,1 +v1anneal_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@1,all,0.577172256097561,0.031047601069063204,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/e807e745fc_2026-10-08T23-06-45.387111.json,1791500507.8519003,1 +v1anneal_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@16,all,0.8206168224365658,0.02899665215198002,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/e807e745fc_2026-10-08T23-06-45.387111.json,1791500507.8519003,1 +v1anneal_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@1,all,0.3049757281553398,0.018235562012432375,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c6b6b96f63_2026-10-08T23-35-31.624764.json,1791500509.6020916,1 +v1anneal_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@4,all,0.3825242718446602,0.021436697747095657,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c6b6b96f63_2026-10-08T23-35-31.624764.json,1791500509.6020916,1 +v1anneal_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,think_closed,all,0.3713592233009709,0.019488767353980033,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/c6b6b96f63_2026-10-08T23-35-31.624764.json,1791500509.6020916,1 +v1anneal_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@1,all,0.20303326810176126,0.01656344982572997,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b330ced5cd_2026-10-08T23-13-49.979042.json,1791500648.0251834,1 +v1anneal_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@4,all,0.24875594073245735,0.01872284210692848,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b330ced5cd_2026-10-08T23-13-49.979042.json,1791500648.0251834,1 +v1anneal_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@1,all,0.744,0.017876440760636245,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/5df6b671e0_2026-10-08T23-24-24.618040.json,1791500506.4109051,1 +v1anneal_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@4,all,0.806,0.017701827855304594,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/5df6b671e0_2026-10-08T23-24-24.618040.json,1791500506.4109051,1 +v1anneal_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,think_closed,all,0.75,0.017990199959677444,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/5df6b671e0_2026-10-08T23-24-24.618040.json,1791500506.4109051,1 +v1anneal_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@1,all,0.5889375,0.01951803957048068,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/0ef1b33a8f_2026-10-08T23-09-07.611785.json,1791500519.200998,1 +v1anneal_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@16,all,0.7296162048474082,0.01950219366391821,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/0ef1b33a8f_2026-10-08T23-09-07.611785.json,1791500519.200998,1 +v1anneal_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@1,all,0.076,0.021669065210497065,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f16410248b_2026-10-08T23-13-54.085315.json,1791500509.7205696,1 +v1anneal_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@4,all,0.104,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f16410248b_2026-10-08T23-13-54.085315.json,1791500509.7205696,1 +v1anneal_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,think_closed,all,0.106,0.02463671532358735,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f16410248b_2026-10-08T23-13-54.085315.json,1791500509.7205696,1 +v1anneal_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@1,all,0.8,0.031108550841912753,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b19288c019_2026-10-08T23-08-10.407709.json,1791500509.8530352,1 +v1anneal_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@4,all,0.888,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b19288c019_2026-10-08T23-08-10.407709.json,1791500509.8530352,1 +v1anneal_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,think_closed,all,0.934,0.01730746622405412,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b19288c019_2026-10-08T23-08-10.407709.json,1791500509.8530352,1 +v1anneal_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@1,all,0.226,0.03436333379748565,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/e666d16964_2026-10-08T23-13-30.494071.json,1791500508.0790873,1 +v1anneal_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@4,all,0.296,0.04099409870984186,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/e666d16964_2026-10-08T23-13-30.494071.json,1791500508.0790873,1 +v1anneal_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,think_closed,all,0.304,0.03826731107321487,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/e666d16964_2026-10-08T23-13-30.494071.json,1791500508.0790873,1 +v1anneal_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/dcda5836d8_2026-10-08T23-13-56.381875.json,1791500512.39535,1 +v1anneal_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/dcda5836d8_2026-10-08T23-13-56.381875.json,1791500512.39535,1 +v1anneal_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,think_closed,all,0.032,0.012370620763103043,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/dcda5836d8_2026-10-08T23-13-56.381875.json,1791500512.39535,1 +v1anneal_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@1,all,0.07,0.020790816831383247,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/071ca7a678_2026-10-08T23-13-57.532906.json,1791500500.5058522,1 +v1anneal_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@4,all,0.104,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/071ca7a678_2026-10-08T23-13-57.532906.json,1791500500.5058522,1 +v1anneal_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,think_closed,all,0.108,0.02242118813576468,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/071ca7a678_2026-10-08T23-13-57.532906.json,1791500500.5058522,1 +v1anneal_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@1,all,0.902,0.023052534672757995,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f14637af89_2026-10-08T23-09-01.879459.json,1791500603.4161537,1 +v1anneal_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@4,all,0.968,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f14637af89_2026-10-08T23-09-01.879459.json,1791500603.4161537,1 +v1anneal_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,think_closed,all,0.964,0.015989916177229908,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/f14637af89_2026-10-08T23-09-01.879459.json,1791500603.4161537,1 +v1anneal_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@1,all,0.204,0.029700657101452563,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/57059fa96b_2026-10-08T23-14-00.543065.json,1791500509.1685123,1 +v1anneal_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@4,all,0.336,0.04241728193144408,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/57059fa96b_2026-10-08T23-14-00.543065.json,1791500509.1685123,1 +v1anneal_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,think_closed,all,0.274,0.03243156566699954,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/57059fa96b_2026-10-08T23-14-00.543065.json,1791500509.1685123,1 +v1anneal_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@1,all,0.002,0.002,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a88850616a_2026-10-08T23-15-51.924749.json,1791500619.7390134,1 +v1anneal_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a88850616a_2026-10-08T23-15-51.924749.json,1791500619.7390134,1 +v1anneal_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,think_closed,all,0.02,0.006720215050322471,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/a88850616a_2026-10-08T23-15-51.924749.json,1791500619.7390134,1 +v1anneal_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@1,all,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/de957273eb_2026-10-08T23-14-02.491733.json,1791500509.4917016,1 +v1anneal_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@4,all,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/de957273eb_2026-10-08T23-14-02.491733.json,1791500509.4917016,1 +v1anneal_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,think_closed,all,0.136,0.030783321835464835,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/de957273eb_2026-10-08T23-14-02.491733.json,1791500509.4917016,1 +v1anneal_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@1,all,0.844,0.02581947252153542,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/41571930b3_2026-10-08T23-07-57.093222.json,1791500512.613816,1 +v1anneal_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@4,all,0.944,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/41571930b3_2026-10-08T23-07-57.093222.json,1791500512.613816,1 +v1anneal_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,think_closed,all,0.936,0.017938964619311316,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/41571930b3_2026-10-08T23-07-57.093222.json,1791500512.613816,1 +v1anneal_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@1,all,0.238,0.03417884650463056,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b83c268629_2026-10-08T23-13-42.362306.json,1791500506.544994,1 +v1anneal_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@4,all,0.328,0.04216098180897563,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b83c268629_2026-10-08T23-13-42.362306.json,1791500506.544994,1 +v1anneal_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,think_closed,all,0.308,0.03649303954843815,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b83c268629_2026-10-08T23-13-42.362306.json,1791500506.544994,1 +v1anneal_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@1,all,0.006,0.006,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/05ebdab28c_2026-10-08T23-13-47.778951.json,1791500506.593149,1 +v1anneal_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/05ebdab28c_2026-10-08T23-13-47.778951.json,1791500506.593149,1 +v1anneal_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,think_closed,all,0.03,0.010472698761772856,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/05ebdab28c_2026-10-08T23-13-47.778951.json,1791500506.593149,1 +v1anneal_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@1,all,0.076,0.019924049335802295,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/75d7a32425_2026-10-08T23-13-46.914757.json,1791500508.014373,1 +v1anneal_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@4,all,0.136,0.030783321835464835,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/75d7a32425_2026-10-08T23-13-46.914757.json,1791500508.014373,1 +v1anneal_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,think_closed,all,0.108,0.02131484413842056,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/75d7a32425_2026-10-08T23-13-46.914757.json,1791500508.014373,1 +v1anneal_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@1,all,0.816,0.029803658576022657,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/decf9a09d6_2026-10-08T23-08-18.153018.json,1791500512.7996862,1 +v1anneal_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@4,all,0.896,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/decf9a09d6_2026-10-08T23-08-18.153018.json,1791500512.7996862,1 +v1anneal_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,think_closed,all,0.944,0.015256939193310929,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/decf9a09d6_2026-10-08T23-08-18.153018.json,1791500512.7996862,1 +v1anneal_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@1,all,0.192,0.031126174028900815,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/02117054cf_2026-10-08T23-13-42.415013.json,1791500500.2367296,1 +v1anneal_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@4,all,0.288,0.04066543273291013,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/02117054cf_2026-10-08T23-13-42.415013.json,1791500500.2367296,1 +v1anneal_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,think_closed,all,0.292,0.035325217164823425,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/02117054cf_2026-10-08T23-13-42.415013.json,1791500500.2367296,1 +v1anneal_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1fa5a5b62a_2026-10-08T23-13-47.047180.json,1791500500.6026435,1 +v1anneal_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1fa5a5b62a_2026-10-08T23-13-47.047180.json,1791500500.6026435,1 +v1anneal_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,think_closed,all,0.04,0.012181424250644649,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1fa5a5b62a_2026-10-08T23-13-47.047180.json,1791500500.6026435,1 +v1anneal_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@1,all,0.072,0.020832666655999657,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b655ea7851_2026-10-08T23-14-00.978907.json,1791500507.9278345,1 +v1anneal_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@4,all,0.112,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b655ea7851_2026-10-08T23-14-00.978907.json,1791500507.9278345,1 +v1anneal_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,think_closed,all,0.094,0.021935388994102217,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/b655ea7851_2026-10-08T23-14-00.978907.json,1791500507.9278345,1 +v1anneal_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@1,all,0.82,0.02747432819337753,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/70c89515a9_2026-10-08T23-07-37.956930.json,1791500518.8442109,1 +v1anneal_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@4,all,0.936,0.021979462554702022,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/70c89515a9_2026-10-08T23-07-37.956930.json,1791500518.8442109,1 +v1anneal_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,think_closed,all,0.942,0.01558949191168577,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/70c89515a9_2026-10-08T23-07-37.956930.json,1791500518.8442109,1 +v1anneal_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@1,all,0.186,0.03261505688303902,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/216dbd01c1_2026-10-08T23-13-57.814433.json,1791500521.9373236,1 +v1anneal_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@4,all,0.232,0.037906506378278276,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/216dbd01c1_2026-10-08T23-13-57.814433.json,1791500521.9373236,1 +v1anneal_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,think_closed,all,0.23,0.03530968979683038,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/216dbd01c1_2026-10-08T23-13-57.814433.json,1791500521.9373236,1 +v1anneal_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.006309235422212681,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1cad387268_2026-10-08T23-13-55.539587.json,1791500509.9101825,1 +v1anneal_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1cad387268_2026-10-08T23-13-55.539587.json,1791500509.9101825,1 +v1anneal_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,think_closed,all,0.036,0.014397580441888321,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/1cad387268_2026-10-08T23-13-55.539587.json,1791500509.9101825,1 +v1anneal_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@1,all,0.064,0.01860107523773827,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8a78c55358_2026-10-08T23-14-14.917921.json,1791500512.8121068,1 +v1anneal_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@4,all,0.12,0.029182407426835203,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8a78c55358_2026-10-08T23-14-14.917921.json,1791500512.8121068,1 +v1anneal_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,think_closed,all,0.094,0.02060848556831275,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/8a78c55358_2026-10-08T23-14-14.917921.json,1791500512.8121068,1 +v1anneal_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@1,all,0.854,0.028281990165862365,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/11e69e72d2_2026-10-08T23-09-43.155470.json,1791500644.010761,1 +v1anneal_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@4,all,0.928,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/11e69e72d2_2026-10-08T23-09-43.155470.json,1791500644.010761,1 +v1anneal_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,think_closed,all,0.962,0.015307598787698913,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/11e69e72d2_2026-10-08T23-09-43.155470.json,1791500644.010761,1 +v1anneal_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@1,all,0.168,0.02793656408549959,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/72f18da693_2026-10-08T23-15-37.899084.json,1791500628.23201,1 +v1anneal_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@4,all,0.272,0.03996127157394334,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/72f18da693_2026-10-08T23-15-37.899084.json,1791500628.23201,1 +v1anneal_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,think_closed,all,0.2,0.029784169859063528,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/72f18da693_2026-10-08T23-15-37.899084.json,1791500628.23201,1 +v1anneal_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/278d66246c_2026-10-08T23-15-30.335953.json,1791500603.2780662,1 +v1anneal_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/278d66246c_2026-10-08T23-15-30.335953.json,1791500603.2780662,1 +v1anneal_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,think_closed,all,0.024,0.009598386961258882,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v1anneal_merge3_116k_120k/cot/2026-10-09-00-52-18/results/278d66246c_2026-10-08T23-15-30.335953.json,1791500603.2780662,1 diff --git a/results/v2anneal_120k.flag-evals-438.tasks.csv b/results/v2anneal_120k.flag-evals-471.tasks.csv similarity index 50% rename from results/v2anneal_120k.flag-evals-438.tasks.csv rename to results/v2anneal_120k.flag-evals-471.tasks.csv index 589a3f4..9110e44 100644 --- a/results/v2anneal_120k.flag-evals-438.tasks.csv +++ b/results/v2anneal_120k.flag-evals-471.tasks.csv @@ -1,2023 +1,2124 @@ checkpoint,task,n_shot,harness,backend,is_group,metric,filter,value,stderr,n_samples,results_file,result_time,n_files -v2anneal_120k,AIME24,0,Evalchemy,vllm,,accuracy_avg,,0.22000000000000003,0.008432740427115679,30,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/27b1296bac/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-41-17.133453.json,1790757672.5467868,1 -v2anneal_120k,AIME24,0,Evalchemy,vllm,,solved_avg,,6.6,,30,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/27b1296bac/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-41-17.133453.json,1790757672.5467868,1 -v2anneal_120k,AIME25,0,Evalchemy,vllm,,accuracy_avg,,0.24,0.004216370213557838,30,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/28cc63de48/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-05-04.293807.json,1790759099.9904187,1 -v2anneal_120k,AIME25,0,Evalchemy,vllm,,solved_avg,,7.2,,30,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/28cc63de48/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-05-04.293807.json,1790759099.9904187,1 -v2anneal_120k,AMC23,0,Evalchemy,vllm,,accuracy_avg,,0.39249999999999996,0.005062114182829147,40,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0554b99f8e/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-27-13.116020.json,1790756828.6413586,1 -v2anneal_120k,AMC23,0,Evalchemy,vllm,,solved_avg,,15.7,,40,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0554b99f8e/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-27-13.116020.json,1790756828.6413586,1 -v2anneal_120k,GPQADiamond,0,Evalchemy,vllm,,accuracy_avg,,0.3434343434343434,0.009523323652344071,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d346c086c7/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-50-00.687837.json,1790758194.75484,1 -v2anneal_120k,GPQADiamond,0,Evalchemy,vllm,,solved_avg,,68.0,,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d346c086c7/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-50-00.687837.json,1790758194.75484,1 -v2anneal_120k,HumanEval,0,Evalchemy,vllm,,python_pass@1,,0.25609756097560976,,164,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/92c34ae84f/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T07-41-37.027671.json,1790754093.3926637,1 -v2anneal_120k,HumanEval,0,Evalchemy,vllm,,sh_pass@1,,0.012658227848101266,,164,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/92c34ae84f/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T07-41-37.027671.json,1790754093.3926637,1 -v2anneal_120k,JEEBench,0,Evalchemy,vllm,,accuracy_avg,,0.2692556634304207,0.004624171574833398,515,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c51beb60f/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-08-56.095234.json,1790759332.2178957,1 -v2anneal_120k,JEEBench,0,Evalchemy,vllm,,solved_avg,,138.66666666666666,,515,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c51beb60f/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-08-56.095234.json,1790759332.2178957,1 -v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_avg,,0.19145466405740377,0.0024450965184594016,511,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 -v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_easy_avg,,0.4157509157509158,0.0027165562223793655,511,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 -v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_hard_avg,,0.0,0.0,511,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 -v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_medium_avg,,0.10760517799352749,0.004045307443365696,511,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 -v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,solved_avg,,97.83333333333333,,511,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 -v2anneal_120k,MATH500,0,Evalchemy,vllm,,accuracy,,0.418,,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b858c978b/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-35-09.998788.json,1790757305.6495829,1 -v2anneal_120k,MATH500,0,Evalchemy,vllm,,num_solved,,209,,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b858c978b/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-35-09.998788.json,1790757305.6495829,1 -v2anneal_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc,none,0.2782608695652174,0.029614094221633747,230,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dc41e26809_2026-09-30T08-33-00.824285.json,1790757010.5143375,1 -v2anneal_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc_norm,none,0.25217391304347825,0.028696745294493314,230,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dc41e26809_2026-09-30T08-33-00.824285.json,1790757010.5143375,1 -v2anneal_120k,arc_challenge,10,lm-eval,vllm,,acc,none,0.6305460750853242,0.014104578366491963,1172,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/51f856ea82_2026-09-30T08-26-38.967814.json,1790756611.5582352,1 -v2anneal_120k,arc_challenge,10,lm-eval,vllm,,acc_norm,none,0.6612627986348123,0.013830568927974365,1172,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/51f856ea82_2026-09-30T08-26-38.967814.json,1790756611.5582352,1 -v2anneal_120k,arc_challenge,25,lm-eval,vllm,,acc,none,0.6390784982935154,0.014034761386175525,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge,25,lm-eval,vllm,,acc_norm,none,0.6680887372013652,0.01376098820088056,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc,none,0.5494880546075085,0.01453964609847157,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc_norm,none,0.5827645051194539,0.014409825518403108,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc,none,0.552901023890785,0.01452938016052677,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc_norm,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc,none,0.5477815699658704,0.014544519880633823,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc_norm,none,0.5802047781569966,0.014422181226303012,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc,none,0.5213310580204779,0.014598087973127125,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc_norm,none,0.5571672354948806,0.01451557387334892,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc,none,0.5187713310580204,0.01460109015063406,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc_norm,none,0.5631399317406144,0.014494421584256512,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc,none,0.575938566552901,0.014441889627464344,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc_norm,none,0.6194539249146758,0.014188277712349937,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc,none,0.5093856655290102,0.014608816322065041,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc_norm,none,0.523037542662116,0.014595873205358168,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc,none,0.4803754266211604,0.014600132075947018,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc_norm,none,0.5315699658703071,0.014582236460866984,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc,none,0.5699658703071673,0.01446763155913799,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc_norm,none,0.60580204778157,0.014280522667467148,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc,none,0.5042662116040956,0.014610858923956936,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc_norm,none,0.5452218430034129,0.014551507060836232,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc,none,0.49573378839590443,0.014610858923956936,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc_norm,none,0.5298634812286689,0.014585305840007116,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc,none,0.5708191126279863,0.014464085894870677,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc_norm,none,0.6023890784982935,0.014301752223279514,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc,none,0.5349829351535836,0.014575583922019714,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc_norm,none,0.5546075085324232,0.014523987638344072,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc,none,0.515358361774744,0.014604496129394757,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc_norm,none,0.5392491467576792,0.014566303676636534,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc,none,0.5418088737201365,0.014560220308714553,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc_norm,none,0.5750853242320819,0.014445698968520807,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc,none,0.5392491467576792,0.014566303676636534,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc_norm,none,0.5656996587030717,0.014484703048857371,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc,none,0.537542662116041,0.014570144495075503,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc_norm,none,0.5537542662116041,0.014526705548539945,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc_norm,none,0.621160409556314,0.01417591549000027,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc,none,0.5563139931740614,0.014518421825670504,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc_norm,none,0.5878839590443686,0.014383915302225435,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc,none,0.5503412969283277,0.014537144444284783,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc_norm,none,0.5784982935153583,0.014430197069326087,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc,none,0.5349829351535836,0.014575583922019714,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc_norm,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc,none,0.5349829351535836,0.014575583922019714,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc_norm,none,0.5827645051194539,0.014409825518403108,1172,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 -v2anneal_120k,arc_easy,10,lm-eval,vllm,,acc,none,0.8691077441077442,0.006920890518900526,2376,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2d96d78293_2026-09-30T08-43-31.066314.json,1790757595.9904432,1 -v2anneal_120k,arc_easy,10,lm-eval,vllm,,acc_norm,none,0.8796296296296297,0.006676946806414794,2376,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2d96d78293_2026-09-30T08-43-31.066314.json,1790757595.9904432,1 -v2anneal_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc,none,0.8944444444444445,0.010247959196000194,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/613b0f3dfe_2026-09-30T07-34-54.848787.json,1790753516.9584126,1 -v2anneal_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc_norm,none,0.8944444444444445,0.010247959196000194,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/613b0f3dfe_2026-09-30T07-34-54.848787.json,1790753516.9584126,1 -v2anneal_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc,none,0.9077777777777778,0.009650009016958635,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6a8c6fb64f_2026-09-30T08-14-38.321906.json,1790755618.6065273,1 -v2anneal_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc_norm,none,0.9077777777777778,0.009650009016958635,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6a8c6fb64f_2026-09-30T08-14-38.321906.json,1790755618.6065273,1 -v2anneal_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8499de27b5_2026-09-30T07-44-55.489804.json,1790754113.7732503,1 -v2anneal_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc_norm,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8499de27b5_2026-09-30T07-44-55.489804.json,1790754113.7732503,1 -v2anneal_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/45935620da_2026-09-30T07-42-41.324231.json,1790753987.35326,1 -v2anneal_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc_norm,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/45935620da_2026-09-30T07-42-41.324231.json,1790753987.35326,1 -v2anneal_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8107e3c5e4_2026-09-30T08-20-49.335447.json,1790756205.6269324,1 -v2anneal_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc_norm,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8107e3c5e4_2026-09-30T08-20-49.335447.json,1790756205.6269324,1 -v2anneal_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc,none,0.9322222222222222,0.008383464750361901,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ea0903b3ae_2026-09-30T08-37-33.320814.json,1790757281.0689347,1 -v2anneal_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc_norm,none,0.9322222222222222,0.008383464750361901,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ea0903b3ae_2026-09-30T08-37-33.320814.json,1790757281.0689347,1 -v2anneal_120k,belebele_est_Latn,5,lm-eval,vllm,,acc,none,0.8777777777777778,0.010924146933565216,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/04aea63d6a_2026-09-30T07-34-31.286385.json,1790753469.2925987,1 -v2anneal_120k,belebele_est_Latn,5,lm-eval,vllm,,acc_norm,none,0.8777777777777778,0.010924146933565216,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/04aea63d6a_2026-09-30T07-34-31.286385.json,1790753469.2925987,1 -v2anneal_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc,none,0.8833333333333333,0.010706705536407178,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c805fed593_2026-09-30T08-37-40.708380.json,1790757279.8233929,1 -v2anneal_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc_norm,none,0.8833333333333333,0.010706705536407178,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c805fed593_2026-09-30T08-37-40.708380.json,1790757279.8233929,1 -v2anneal_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc,none,0.9166666666666666,0.009217969157169261,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/33a8c0cba3_2026-09-30T08-27-09.656549.json,1790756643.080764,1 -v2anneal_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc_norm,none,0.9166666666666666,0.009217969157169261,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/33a8c0cba3_2026-09-30T08-27-09.656549.json,1790756643.080764,1 -v2anneal_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc,none,0.8844444444444445,0.010662298780233998,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f781842a99_2026-09-30T08-47-51.193601.json,1790757887.8456812,1 -v2anneal_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc_norm,none,0.8844444444444445,0.010662298780233998,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f781842a99_2026-09-30T08-47-51.193601.json,1790757887.8456812,1 -v2anneal_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3bf2964e48_2026-09-30T08-17-02.646892.json,1790756046.3326223,1 -v2anneal_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc_norm,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3bf2964e48_2026-09-30T08-17-02.646892.json,1790756046.3326223,1 -v2anneal_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3a159b4c87_2026-09-30T08-17-15.343677.json,1790756046.335199,1 -v2anneal_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc_norm,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3a159b4c87_2026-09-30T08-17-15.343677.json,1790756046.335199,1 -v2anneal_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7664f00e89_2026-09-30T08-52-30.676840.json,1790758109.0038042,1 -v2anneal_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc_norm,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7664f00e89_2026-09-30T08-52-30.676840.json,1790758109.0038042,1 -v2anneal_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1d4aaac975_2026-09-30T08-27-09.934934.json,1790756652.7021835,1 -v2anneal_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc_norm,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1d4aaac975_2026-09-30T08-27-09.934934.json,1790756652.7021835,1 -v2anneal_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5cafe66f64_2026-09-30T07-34-25.177521.json,1790753469.394227,1 -v2anneal_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc_norm,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5cafe66f64_2026-09-30T07-34-25.177521.json,1790753469.394227,1 -v2anneal_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.010481480680812848,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c5a24491f_2026-09-30T08-36-39.689261.json,1790757138.5261528,1 -v2anneal_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc_norm,none,0.8888888888888888,0.010481480680812848,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c5a24491f_2026-09-30T08-36-39.689261.json,1790757138.5261528,1 -v2anneal_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6cfede2de_2026-09-30T08-43-40.609122.json,1790757623.3662093,1 -v2anneal_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc_norm,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6cfede2de_2026-09-30T08-43-40.609122.json,1790757623.3662093,1 -v2anneal_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9ed7ef48b2_2026-09-30T07-40-47.590000.json,1790753866.4226592,1 -v2anneal_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc_norm,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9ed7ef48b2_2026-09-30T07-40-47.590000.json,1790753866.4226592,1 -v2anneal_120k,belebele_por_Latn,5,lm-eval,vllm,,acc,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d96ffe17ac_2026-09-30T08-27-13.949496.json,1790756652.0558429,1 -v2anneal_120k,belebele_por_Latn,5,lm-eval,vllm,,acc_norm,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d96ffe17ac_2026-09-30T08-27-13.949496.json,1790756652.0558429,1 -v2anneal_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc,none,0.9044444444444445,0.009804807528775588,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6c806908d3_2026-09-30T07-42-49.499385.json,1790753987.0305846,1 -v2anneal_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc_norm,none,0.9044444444444445,0.009804807528775588,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6c806908d3_2026-09-30T07-42-49.499385.json,1790753987.0305846,1 -v2anneal_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc,none,0.8933333333333333,0.010295354033282278,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/01a47b8165_2026-09-30T07-34-51.551218.json,1790753511.7604973,1 -v2anneal_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc_norm,none,0.8933333333333333,0.010295354033282278,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/01a47b8165_2026-09-30T07-34-51.551218.json,1790753511.7604973,1 -v2anneal_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c201cc0f3f_2026-09-30T07-40-53.615461.json,1790753873.9768434,1 -v2anneal_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc_norm,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c201cc0f3f_2026-09-30T07-40-53.615461.json,1790753873.9768434,1 -v2anneal_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6addf594cf_2026-09-30T07-40-46.872580.json,1790753866.0631695,1 -v2anneal_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc_norm,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6addf594cf_2026-09-30T07-40-46.872580.json,1790753866.0631695,1 -v2anneal_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc,none,0.8855555555555555,0.010617576963634174,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a987d2decb_2026-09-30T08-14-26.337113.json,1790755617.4652393,1 -v2anneal_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc_norm,none,0.8855555555555555,0.010617576963634174,900,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a987d2decb_2026-09-30T08-14-26.337113.json,1790755617.4652393,1 -v2anneal_120k,bigbench_cs_algorithms_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7818181818181819,0.011372076264788566,1320,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/45e5c4e471_2026-09-30T16-51-22.331879.json,1790786897.8896616,1 -v2anneal_120k,bigbench_dyck_languages_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.636,0.015222868840522022,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c9d8f057ca_2026-09-30T07-35-00.931103.json,1790753514.1676912,1 -v2anneal_120k,bigbench_language_identification_multiple_choice,10,lm-eval,vllm,,acc,none,0.2629,0.004402305876436003,10000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0d6d9413fa_2026-09-30T09-11-48.610799.json,1790755619.9956675,1 -v2anneal_120k,bigbench_operators_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.8285714285714286,0.026069544122384443,210,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c364babeaf_2026-09-30T07-42-43.932264.json,1790753986.5193744,1 -v2anneal_120k,bigbench_qa_wikidata_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7232419664386596,0.003138557397975128,20321,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3073f1e8f6_2026-09-30T08-41-26.495060.json,1790757384.0517612,1 -v2anneal_120k,bigbench_repeat_copy_logic_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.65625,0.08530513305661301,32,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f8e047b339_2026-09-30T08-10-56.455424.json,1790754227.1787226,1 -v2anneal_120k,boolq,10,lm-eval,vllm,,acc,none,0.864525993883792,0.005985625684183008,3270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d015723bc4_2026-09-30T07-43-28.095124.json,1790753864.779276,1 -v2anneal_120k,commonsense_qa,10,lm-eval,vllm,,acc,none,0.8263718263718264,0.01084470978346005,1221,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/52b57f11d3_2026-09-30T08-33-21.133337.json,1790757011.7022827,1 -v2anneal_120k,copa,0,lm-eval,vllm,,acc,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a9afe81490_2026-09-30T07-38-31.073944.json,1790753750.935608,1 -v2anneal_120k,coqa,0,lm-eval,vllm,,em,none,0.7075,0.016618961452495126,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8a8c6d6016_2026-09-30T08-14-35.743007.json,1790755618.6579852,1 -v2anneal_120k,coqa,0,lm-eval,vllm,,f1,none,0.8275709618300378,0.011891552197371301,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8a8c6d6016_2026-09-30T08-14-35.743007.json,1790755618.6579852,1 -v2anneal_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.49580368982227,0.017873768942221237,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/97856f122e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-58.405051.json,1790755604.83264,1 -v2anneal_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7118872153187481,0.003838496595288138,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/97856f122e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-58.405051.json,1790755604.83264,1 -v2anneal_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2712393810193638,0.006100325037255695,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/97856f122e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-58.405051.json,1790755604.83264,1 -v2anneal_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.43463242062653,0.011983123071398632,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/97856f122e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-58.405051.json,1790755604.83264,1 -v2anneal_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.0837927584148,0.01900944324996355,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/62d25d021e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-42.466835.json,1790753923.444419,1 -v2anneal_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7152651854832485,0.003807541510780792,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/62d25d021e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-42.466835.json,1790753923.444419,1 -v2anneal_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28457543007268465,0.006312256117436793,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/62d25d021e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-42.466835.json,1790753923.444419,1 -v2anneal_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.32752519730818,0.011885459416232843,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/62d25d021e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-42.466835.json,1790753923.444419,1 -v2anneal_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.42367496389634,0.01741317195765659,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6a7be9ecd8/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-37.582841.json,1790753798.71417,1 -v2anneal_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7045446152034913,0.00393158895434034,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6a7be9ecd8/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-37.582841.json,1790753798.71417,1 -v2anneal_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2641951550601192,0.006118162950569426,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6a7be9ecd8/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-37.582841.json,1790753798.71417,1 -v2anneal_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.34228727089832,0.011576837204037784,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6a7be9ecd8/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-37.582841.json,1790753798.71417,1 -v2anneal_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,49.90526944339191,0.019459720639379043,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2fac1223dc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-44.748260.json,1790754045.580605,1 -v2anneal_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7376749653756199,0.0039500704346317975,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2fac1223dc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-44.748260.json,1790754045.580605,1 -v2anneal_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.32819516532560894,0.007037623120173013,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2fac1223dc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-44.748260.json,1790754045.580605,1 -v2anneal_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.68782589373826,0.012867514415585816,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2fac1223dc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-44.748260.json,1790754045.580605,1 -v2anneal_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.306161372283775,0.017919427535563137,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5802d24f50/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-13.032007.json,1790755604.832521,1 -v2anneal_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6930665209153473,0.004047831200697218,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5802d24f50/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-13.032007.json,1790755604.832521,1 -v2anneal_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2624424313890465,0.006277519586993478,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5802d24f50/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-13.032007.json,1790755604.832521,1 -v2anneal_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.05500987803457,0.012484208859652502,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5802d24f50/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-13.032007.json,1790755604.832521,1 -v2anneal_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,52.07458177483599,0.01954214599031202,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/868240b59e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-48.489108.json,1790753929.638437,1 -v2anneal_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7521626757288533,0.003963678025629041,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/868240b59e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-48.489108.json,1790753929.638437,1 -v2anneal_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3526253126244304,0.006854576306568215,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/868240b59e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-48.489108.json,1790753929.638437,1 -v2anneal_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.34284067643034,0.012926175023147923,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/868240b59e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-48.489108.json,1790753929.638437,1 -v2anneal_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.77153746557002,0.019997646277299157,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/83acc65062/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-19.329270.json,1790754320.5156,1 -v2anneal_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7199822560808736,0.003946190126963025,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/83acc65062/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-19.329270.json,1790754320.5156,1 -v2anneal_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29303849374333246,0.006638864326959291,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/83acc65062/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-19.329270.json,1790754320.5156,1 -v2anneal_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.54310382172478,0.01318103809292999,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/83acc65062/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-19.329270.json,1790754320.5156,1 -v2anneal_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.24450193449369,0.018418504777938455,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/da34212f99/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-06.030421.json,1790753826.896236,1 -v2anneal_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6604099366023057,0.004243523631815729,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/da34212f99/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-06.030421.json,1790753826.896236,1 -v2anneal_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22491076407610824,0.005875695156917328,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/da34212f99/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-06.030421.json,1790753826.896236,1 -v2anneal_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.82389474922735,0.013334127748540073,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/da34212f99/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-06.030421.json,1790753826.896236,1 -v2anneal_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu,none,34.34810837932732,0.015673249846027575,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/100817f5f2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-13.796090.json,1790755935.010898,1 -v2anneal_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6266520773549422,0.0037974043804741156,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/100817f5f2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-13.796090.json,1790755935.010898,1 -v2anneal_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18119622387295137,0.004817695652105389,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/100817f5f2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-13.796090.json,1790755935.010898,1 -v2anneal_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.24570032843578,0.010872700638926718,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/100817f5f2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-13.796090.json,1790755935.010898,1 -v2anneal_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu,none,32.44275166580018,0.01708217833414928,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d4a137fd18/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-49.753349.json,1790754350.573568,1 -v2anneal_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5993013544757751,0.004469414487816768,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d4a137fd18/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-49.753349.json,1790754350.573568,1 -v2anneal_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1682303383767639,0.005017110312991332,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d4a137fd18/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-49.753349.json,1790754350.573568,1 -v2anneal_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.238709746920456,0.011808811167419369,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d4a137fd18/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-49.753349.json,1790754350.573568,1 -v2anneal_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu,none,40.977533762594234,0.018242374089000462,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/742bd88dc6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-00.111172.json,1790753820.951066,1 -v2anneal_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6603498488209074,0.004036848408145262,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/742bd88dc6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-00.111172.json,1790753820.951066,1 -v2anneal_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.22761679177035632,0.005552314488177307,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/742bd88dc6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-00.111172.json,1790753820.951066,1 -v2anneal_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,64.56087793380667,0.012158827122996733,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/742bd88dc6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-00.111172.json,1790753820.951066,1 -v2anneal_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu,none,43.94335458619114,0.01840736887597285,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c89ad84608/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-52.201792.json,1790787233.013158,1 -v2anneal_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6776344541062229,0.004247519045625766,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c89ad84608/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-52.201792.json,1790787233.013158,1 -v2anneal_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.27206862365596923,0.006205343274531046,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c89ad84608/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-52.201792.json,1790787233.013158,1 -v2anneal_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.28053789603096,0.013080664164927223,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c89ad84608/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-52.201792.json,1790787233.013158,1 -v2anneal_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu,none,33.19507600380193,0.019967403691796542,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f137d087be/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-14.620535.json,1790787195.418929,1 -v2anneal_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5925897258332335,0.004999658943907772,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f137d087be/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-14.620535.json,1790787195.418929,1 -v2anneal_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17499534461243696,0.005903880028179754,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f137d087be/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-14.620535.json,1790787195.418929,1 -v2anneal_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.04064560293918,0.014352815200572872,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f137d087be/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-14.620535.json,1790787195.418929,1 -v2anneal_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu,none,48.24650963253074,0.019991003571247386,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1f67b2d42b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-49.045074.json,1790753930.044486,1 -v2anneal_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7103266641590754,0.004446787475179131,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1f67b2d42b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-49.045074.json,1790753930.044486,1 -v2anneal_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.32011268264551596,0.007182919511333117,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1f67b2d42b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-49.045074.json,1790753930.044486,1 -v2anneal_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.99200396470036,0.012742183241793886,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1f67b2d42b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-49.045074.json,1790753930.044486,1 -v2anneal_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu,none,40.3284618211959,0.021793380199684662,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/782ee0535a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-42-35.179678.json,1790754156.154241,1 -v2anneal_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6520394512492752,0.004760723708908364,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/782ee0535a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-42-35.179678.json,1790754156.154241,1 -v2anneal_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23916561451070997,0.006652813835001809,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/782ee0535a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-42-35.179678.json,1790754156.154241,1 -v2anneal_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.71229578057241,0.014537540107628538,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/782ee0535a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-42-35.179678.json,1790754156.154241,1 -v2anneal_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu,none,26.722934187458257,0.01483519493786614,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d6616a05f6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-12.192110.json,1790753953.082434,1 -v2anneal_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_1,none,0.535306595896592,0.004457396447240381,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d6616a05f6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-12.192110.json,1790753953.082434,1 -v2anneal_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_4,none,0.12468133087399706,0.004055284960251834,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d6616a05f6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-12.192110.json,1790753953.082434,1 -v2anneal_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,chrf++,rescored,51.00912754856832,0.012682127454018725,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d6616a05f6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-12.192110.json,1790753953.082434,1 -v2anneal_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu,none,27.04193752782002,0.01893830358741019,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/87bd680b8b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-36.327923.json,1790753857.186767,1 -v2anneal_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5545080960179309,0.005091752878951199,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/87bd680b8b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-36.327923.json,1790753857.186767,1 -v2anneal_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12737340838451433,0.005329779687111957,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/87bd680b8b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-36.327923.json,1790753857.186767,1 -v2anneal_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.98100090404032,0.013432752238009833,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/87bd680b8b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-36.327923.json,1790753857.186767,1 -v2anneal_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu,none,19.017225953764598,0.016448588926211965,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b9871a2774/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-14.199749.json,1790755935.39876,1 -v2anneal_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.48658554524018605,0.004723198957426475,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b9871a2774/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-14.199749.json,1790755935.39876,1 -v2anneal_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.07534446340487928,0.00403695281589065,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b9871a2774/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-14.199749.json,1790755935.39876,1 -v2anneal_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,52.01409233452421,0.012258078254741593,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b9871a2774/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-14.199749.json,1790755935.39876,1 -v2anneal_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu,none,25.28029146372687,0.018862396009194125,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf58aa3504/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-03.805065.json,1790755604.832239,1 -v2anneal_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5253447605478087,0.005212699492775908,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf58aa3504/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-03.805065.json,1790755604.832239,1 -v2anneal_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11615325833822131,0.0051361713817452866,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf58aa3504/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-03.805065.json,1790755604.832239,1 -v2anneal_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.2619176675131,0.012765988257010296,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf58aa3504/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-03.805065.json,1790755604.832239,1 -v2anneal_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu,none,51.437044559979796,0.023397362574870278,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6ae4fdcb21/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-39.504974.json,1790754040.345049,1 -v2anneal_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7039715962556076,0.004965053434555822,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6ae4fdcb21/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-39.504974.json,1790754040.345049,1 -v2anneal_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.36765640656952586,0.008097418223210674,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6ae4fdcb21/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-39.504974.json,1790754040.345049,1 -v2anneal_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.15634898947863,0.015595454506079461,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6ae4fdcb21/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-39.504974.json,1790754040.345049,1 -v2anneal_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu,none,30.38059405518762,0.018043960529600268,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f64b93f7bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.383552.json,1790755933.598349,1 -v2anneal_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5732688810364633,0.004567025939936597,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f64b93f7bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.383552.json,1790755933.598349,1 -v2anneal_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.15546043454523317,0.0051111730280654155,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f64b93f7bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.383552.json,1790755933.598349,1 -v2anneal_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.20388049578169,0.013667735602082568,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f64b93f7bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.383552.json,1790755933.598349,1 -v2anneal_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu,none,37.292359089171015,0.016269411717259426,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/39477b29a6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-38.980260.json,1790753920.263699,1 -v2anneal_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6408040848328898,0.0037472821379716183,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/39477b29a6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-38.980260.json,1790753920.263699,1 -v2anneal_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20900268231538094,0.00542243395325613,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/39477b29a6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-38.980260.json,1790753920.263699,1 -v2anneal_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.10011626842501,0.010838764463706421,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/39477b29a6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-38.980260.json,1790753920.263699,1 -v2anneal_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.914863156008273,0.019470083119627644,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3c6e6078ce/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-16.146249.json,1790755936.988646,1 -v2anneal_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5776683581932528,0.00499144370529589,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3c6e6078ce/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-16.146249.json,1790755936.988646,1 -v2anneal_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1661789724637024,0.005539426265331667,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3c6e6078ce/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-16.146249.json,1790755936.988646,1 -v2anneal_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.38864956997195,0.013834303997904395,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3c6e6078ce/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-16.146249.json,1790755936.988646,1 -v2anneal_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu,none,26.203875784161635,0.017904273605822658,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71d5d8c30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-55.643818.json,1790753876.458679,1 -v2anneal_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5568536121165085,0.004387278061870514,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71d5d8c30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-55.643818.json,1790753876.458679,1 -v2anneal_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11010147312298672,0.004284230679638809,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71d5d8c30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-55.643818.json,1790753876.458679,1 -v2anneal_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.62700259181234,0.012105681372653592,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71d5d8c30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-55.643818.json,1790753876.458679,1 -v2anneal_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu,none,28.308020085529474,0.019836388925355077,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d9dbb473d1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-40.085809.json,1790753860.921484,1 -v2anneal_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.539677720527927,0.0049180499389946605,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d9dbb473d1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-40.085809.json,1790753860.921484,1 -v2anneal_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1420727850523423,0.005378353173830976,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d9dbb473d1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-40.085809.json,1790753860.921484,1 -v2anneal_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,52.53371289612861,0.014519112035408436,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d9dbb473d1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-40.085809.json,1790753860.921484,1 -v2anneal_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu,none,32.43650110038292,0.014847283970080904,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0df7149da6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-45.730797.json,1790753807.241788,1 -v2anneal_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5940355060149777,0.0038031060668150597,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0df7149da6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-45.730797.json,1790753807.241788,1 -v2anneal_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16404111384842315,0.004190850645763976,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0df7149da6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-45.730797.json,1790753807.241788,1 -v2anneal_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.856350640573794,0.010226265067883239,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0df7149da6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-45.730797.json,1790753807.241788,1 -v2anneal_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu,none,3.6510066586646763,0.007230547759205677,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cddef4a943/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-39-40.528888.json,1790757581.086417,1 -v2anneal_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_1,none,0.22312185261551548,0.0040433214907522564,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cddef4a943/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-39-40.528888.json,1790757581.086417,1 -v2anneal_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_4,none,0.005980471872460149,0.0009257656166834676,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cddef4a943/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-39-40.528888.json,1790757581.086417,1 -v2anneal_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,chrf++,rescored,26.967176626606914,0.00961829563172114,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cddef4a943/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-39-40.528888.json,1790757581.086417,1 -v2anneal_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu,none,26.63099599780555,0.01965041988502942,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b623591db4/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-07.585462.json,1790787248.378122,1 -v2anneal_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5440562083797443,0.00506520640228864,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b623591db4/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-07.585462.json,1790787248.378122,1 -v2anneal_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12574840988146457,0.005185630972930373,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b623591db4/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-07.585462.json,1790787248.378122,1 -v2anneal_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.58147783640398,0.013731914055818716,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b623591db4/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-07.585462.json,1790787248.378122,1 -v2anneal_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu,none,31.41956023085231,0.01966182777923508,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/60377d430a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-16.378583.json,1790754017.600008,1 -v2anneal_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.591530405522697,0.005211799547104305,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/60377d430a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-16.378583.json,1790754017.600008,1 -v2anneal_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16726250061385084,0.006295512472582018,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/60377d430a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-16.378583.json,1790754017.600008,1 -v2anneal_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.772593442124744,0.014330847238355064,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/60377d430a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-16.378583.json,1790754017.600008,1 -v2anneal_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu,none,35.948434858408184,0.01712441088605186,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/811d352406/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-42.841112.json,1790753864.023363,1 -v2anneal_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6291440753651142,0.0039286277319916995,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/811d352406/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-42.841112.json,1790753864.023363,1 -v2anneal_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.19068255387190997,0.005074844590141389,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/811d352406/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-42.841112.json,1790753864.023363,1 -v2anneal_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,61.80757771603616,0.01139594714054676,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/811d352406/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-42.841112.json,1790753864.023363,1 -v2anneal_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu,none,39.81325432987597,0.019474183513544588,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf35b1f259/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-15.146608.json,1790754315.973067,1 -v2anneal_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6518743194398726,0.004669348639634521,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf35b1f259/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-15.146608.json,1790754315.973067,1 -v2anneal_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23676608501773977,0.006543879552104657,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf35b1f259/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-15.146608.json,1790754315.973067,1 -v2anneal_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.83181844585137,0.013570389571438022,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf35b1f259/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-15.146608.json,1790754315.973067,1 -v2anneal_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu,none,28.258407528723023,0.016400869958964597,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/af46d37edf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-08.673828.json,1790753829.531919,1 -v2anneal_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5791834751000696,0.004332622471820654,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/af46d37edf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-08.673828.json,1790753829.531919,1 -v2anneal_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1310919790194132,0.004535474074649744,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/af46d37edf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-08.673828.json,1790753829.531919,1 -v2anneal_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.291593197460934,0.011776753917940525,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/af46d37edf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-08.673828.json,1790753829.531919,1 -v2anneal_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu,none,34.24295360309306,0.015618936952799221,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/4d2a380287/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-43.693963.json,1790753804.485438,1 -v2anneal_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6132380607421881,0.0037918610297687947,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/4d2a380287/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-43.693963.json,1790753804.485438,1 -v2anneal_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16947512140679397,0.004482663331885258,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/4d2a380287/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-43.693963.json,1790753804.485438,1 -v2anneal_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.97515002289126,0.010774043539282019,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/4d2a380287/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-43.693963.json,1790753804.485438,1 -v2anneal_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu,none,22.542720524534232,0.016334239809939807,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/8b1db287a7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-39.180462.json,1790753800.301554,1 -v2anneal_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.49873710245198694,0.004634418977591393,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/8b1db287a7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-39.180462.json,1790753800.301554,1 -v2anneal_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.09677448140886817,0.00412668462400495,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/8b1db287a7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-39.180462.json,1790753800.301554,1 -v2anneal_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,49.326547210138365,0.012305609815876906,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/8b1db287a7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-39.180462.json,1790753800.301554,1 -v2anneal_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu,none,50.01801630450886,0.02085842614303581,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/652022919b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-06.169464.json,1790753947.784885,1 -v2anneal_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7258543146916152,0.004489579634100495,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/652022919b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-06.169464.json,1790753947.784885,1 -v2anneal_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3378748684347292,0.007521553933890442,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/652022919b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-06.169464.json,1790753947.784885,1 -v2anneal_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.86996858985057,0.013644518484891012,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/652022919b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-06.169464.json,1790753947.784885,1 -v2anneal_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu,none,40.724795465499504,0.018535565825811697,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f057e31b81/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-26.008788.json,1790753846.865132,1 -v2anneal_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6507707425824585,0.004515391084555917,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f057e31b81/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-26.008788.json,1790753846.865132,1 -v2anneal_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2498325580898546,0.00624045249301115,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f057e31b81/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-26.008788.json,1790753846.865132,1 -v2anneal_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.11015168428755,0.012773885283956583,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f057e31b81/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-26.008788.json,1790753846.865132,1 -v2anneal_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu,none,34.002466404683275,0.020475189790038026,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0e1f710903/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-45.790602.json,1790753987.2999,1 -v2anneal_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5955473965296862,0.005183263487083542,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0e1f710903/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-45.790602.json,1790753987.2999,1 -v2anneal_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18765284888117387,0.006135999674867611,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0e1f710903/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-45.790602.json,1790753987.2999,1 -v2anneal_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.10325192995245,0.014302501611674547,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0e1f710903/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-45.790602.json,1790753987.2999,1 -v2anneal_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.308954244231618,0.018278791569936025,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cf92330f71/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-12.581794.json,1790787193.625231,1 -v2anneal_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.58351468096674,0.004956098934879901,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cf92330f71/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-12.581794.json,1790787193.625231,1 -v2anneal_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16723634939159115,0.0055553764891342035,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cf92330f71/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-12.581794.json,1790787193.625231,1 -v2anneal_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.11508603256207,0.013353601835866242,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cf92330f71/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-12.581794.json,1790787193.625231,1 -v2anneal_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu,none,29.421266555066232,0.013476687986262394,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d726069b65/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-24.942585.json,1790787265.771125,1 -v2anneal_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5790852947910196,0.0035626562308184065,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d726069b65/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-24.942585.json,1790787265.771125,1 -v2anneal_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.13999310452242858,0.003731219206267395,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d726069b65/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-24.942585.json,1790787265.771125,1 -v2anneal_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.790710672646,0.010139415948893928,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d726069b65/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-24.942585.json,1790787265.771125,1 -v2anneal_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu,none,34.6986316113732,0.018381483148175448,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/677c7d2a5b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-35.718156.json,1790753976.917203,1 -v2anneal_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6107355665598778,0.004676663359228811,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/677c7d2a5b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-35.718156.json,1790753976.917203,1 -v2anneal_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.18942250262607296,0.0056823986083420625,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/677c7d2a5b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-35.718156.json,1790753976.917203,1 -v2anneal_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,59.01492077195102,0.01306819966611672,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/677c7d2a5b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-35.718156.json,1790753976.917203,1 -v2anneal_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu,none,46.51667668615471,0.019646228641442397,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f47a1d69bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-49.978716.json,1790753810.825692,1 -v2anneal_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6930778304202803,0.004403820399261887,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f47a1d69bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-49.978716.json,1790753810.825692,1 -v2anneal_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29622339461399244,0.0067583181061484894,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f47a1d69bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-49.978716.json,1790753810.825692,1 -v2anneal_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.83887909826146,0.013076088486436559,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f47a1d69bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-49.978716.json,1790753810.825692,1 -v2anneal_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu,none,25.675682575077705,0.01886822783850094,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d57d6d77fc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-01.610695.json,1790753822.442255,1 -v2anneal_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5435408370237054,0.004964088407358119,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d57d6d77fc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-01.610695.json,1790753822.442255,1 -v2anneal_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1208401211699128,0.005053024895010905,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d57d6d77fc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-01.610695.json,1790753822.442255,1 -v2anneal_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.43194435194783,0.013448661636411197,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d57d6d77fc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-01.610695.json,1790753822.442255,1 -v2anneal_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu,none,30.348223283687727,0.01835249338589849,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/efb928f4d3/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.995737.json,1790755934.084875,1 -v2anneal_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.5572183553655581,0.00492587915523367,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/efb928f4d3/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.995737.json,1790755934.084875,1 -v2anneal_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.15076461683115433,0.005059098560793833,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/efb928f4d3/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.995737.json,1790755934.084875,1 -v2anneal_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,55.44925556557193,0.013399291688297565,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/efb928f4d3/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.995737.json,1790755934.084875,1 -v2anneal_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.074487127638115,0.019369789256980595,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b615bcadf2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-32.950066.json,1790753913.743139,1 -v2anneal_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6747726150556571,0.004240336833844642,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b615bcadf2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-32.950066.json,1790753913.743139,1 -v2anneal_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2323149584026767,0.0061818177647449,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b615bcadf2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-32.950066.json,1790753913.743139,1 -v2anneal_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.731040604969145,0.013222352343258418,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b615bcadf2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-32.950066.json,1790753913.743139,1 -v2anneal_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.29981317709041,0.01856489307447493,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0116a54194/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-41.960894.json,1790753982.955544,1 -v2anneal_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.62883864185062,0.004370637056121874,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0116a54194/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-41.960894.json,1790753982.955544,1 -v2anneal_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18633328699304788,0.005696350283259595,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0116a54194/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-41.960894.json,1790753982.955544,1 -v2anneal_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.04311154978908,0.013335242267227427,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0116a54194/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-41.960894.json,1790753982.955544,1 -v2anneal_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.407741486381816,0.01797126049931097,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d646b2f30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-30.208122.json,1790754271.06476,1 -v2anneal_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.655419615634274,0.0042794860469791965,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d646b2f30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-30.208122.json,1790754271.06476,1 -v2anneal_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21033837291085822,0.005890855551182566,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d646b2f30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-30.208122.json,1790754271.06476,1 -v2anneal_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.781438759198906,0.012722435064938295,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d646b2f30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-30.208122.json,1790754271.06476,1 -v2anneal_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,48.53839164339867,0.02108617852272175,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d35b3d22f1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-00.279514.json,1790753941.114493,1 -v2anneal_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7297896736942243,0.004318623167354128,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d35b3d22f1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-00.279514.json,1790753941.114493,1 -v2anneal_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3225457889352582,0.007230214420901475,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d35b3d22f1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-00.279514.json,1790753941.114493,1 -v2anneal_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.5529485721811,0.014198648475060015,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d35b3d22f1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-00.279514.json,1790753941.114493,1 -v2anneal_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.62793573179996,0.02105160824343241,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b176fe81ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-48.137074.json,1790754288.937839,1 -v2anneal_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7063882323558047,0.0044338567511759495,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b176fe81ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-48.137074.json,1790754288.937839,1 -v2anneal_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2952461608328415,0.007200190494918774,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b176fe81ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-48.137074.json,1790754288.937839,1 -v2anneal_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.36603469849959,0.013968023876800644,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b176fe81ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-48.137074.json,1790754288.937839,1 -v2anneal_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.27680487229327,0.018275602633816567,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/38c804f2fb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-15.848740.json,1790787196.649022,1 -v2anneal_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7106319299227449,0.004036625376460495,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/38c804f2fb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-15.848740.json,1790787196.649022,1 -v2anneal_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28236336434146125,0.006556343274917702,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/38c804f2fb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-15.848740.json,1790787196.649022,1 -v2anneal_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.11906617975623,0.011574616819375789,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/38c804f2fb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-15.848740.json,1790787196.649022,1 -v2anneal_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.391066491334996,0.018852782785640714,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5000354e03/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-18.876533.json,1790754259.737613,1 -v2anneal_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6719679529054059,0.004296638209840715,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5000354e03/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-18.876533.json,1790754259.737613,1 -v2anneal_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2315560147984029,0.006024844726764598,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5000354e03/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-18.876533.json,1790754259.737613,1 -v2anneal_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.65480382415053,0.013508390389602167,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5000354e03/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-18.876533.json,1790754259.737613,1 -v2anneal_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.92337517529059,0.018563578546152083,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/7934fd127e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.584596.json,1790753809.78707,1 -v2anneal_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6551427593508777,0.004347419808816709,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/7934fd127e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.584596.json,1790753809.78707,1 -v2anneal_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2134005838196058,0.0058940947350989426,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/7934fd127e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.584596.json,1790753809.78707,1 -v2anneal_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.946069190386986,0.013324824019329667,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/7934fd127e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.584596.json,1790753809.78707,1 -v2anneal_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.17256351085131,0.019670356639361557,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/770ed48fea/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-44.711006.json,1790754285.581113,1 -v2anneal_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6549619611091593,0.0043867104243482625,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/770ed48fea/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-44.711006.json,1790754285.581113,1 -v2anneal_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22487096279707122,0.0062599327634735805,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/770ed48fea/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-44.711006.json,1790754285.581113,1 -v2anneal_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.65952335450019,0.013329163741625077,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/770ed48fea/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-44.711006.json,1790754285.581113,1 -v2anneal_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.70858443798538,0.01735818023196172,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e5641b92ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-23.233913.json,1790753964.059432,1 -v2anneal_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6529825419376374,0.003930470033693993,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e5641b92ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-23.233913.json,1790753964.059432,1 -v2anneal_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20208083734511054,0.005439165885939003,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e5641b92ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-23.233913.json,1790753964.059432,1 -v2anneal_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.28168522831689,0.012178337844659281,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e5641b92ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-23.233913.json,1790753964.059432,1 -v2anneal_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,21.63253011238874,0.017309103326865607,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/85af07a961/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-18-30.091206.json,1790756310.703851,1 -v2anneal_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5172090645073578,0.0044181804488086915,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/85af07a961/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-18-30.091206.json,1790756310.703851,1 -v2anneal_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.08922988743878141,0.003926348898805715,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/85af07a961/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-18-30.091206.json,1790756310.703851,1 -v2anneal_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,47.76099258182989,0.013364661956292533,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/85af07a961/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-18-30.091206.json,1790756310.703851,1 -v2anneal_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.955862277584835,0.01936428307663298,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e2ea4577e1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-53.432110.json,1790753934.268409,1 -v2anneal_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6415272173858769,0.004524096375448504,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e2ea4577e1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-53.432110.json,1790753934.268409,1 -v2anneal_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20693230471818935,0.006043223982450675,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e2ea4577e1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-53.432110.json,1790753934.268409,1 -v2anneal_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.39515533168688,0.014099394086835849,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e2ea4577e1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-53.432110.json,1790753934.268409,1 -v2anneal_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.14633631433362,0.02006170964535263,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0b28973b54/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-25.576619.json,1790754326.390091,1 -v2anneal_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6717562343595578,0.004412134414647363,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0b28973b54/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-25.576619.json,1790754326.390091,1 -v2anneal_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23384912318470588,0.006397751229584828,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0b28973b54/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-25.576619.json,1790754326.390091,1 -v2anneal_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.69941757019636,0.013870331758271619,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0b28973b54/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-25.576619.json,1790754326.390091,1 -v2anneal_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.43616157099693,0.018664502001151478,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c5a16eaf11/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-46.573663.json,1790753807.430426,1 -v2anneal_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7144934747485994,0.003864228602580939,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c5a16eaf11/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-46.573663.json,1790753807.430426,1 -v2anneal_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2859559242464927,0.00628309998137778,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c5a16eaf11/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-46.573663.json,1790753807.430426,1 -v2anneal_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.09406776782394,0.012419769010781859,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c5a16eaf11/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-46.573663.json,1790753807.430426,1 -v2anneal_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,58.53836612939456,0.01997464882486986,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b4ba980feb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-52.377525.json,1790753813.337132,1 -v2anneal_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7872098797546123,0.0037840251467578007,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b4ba980feb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-52.377525.json,1790753813.337132,1 -v2anneal_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.4259012221431704,0.0076208396358273655,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b4ba980feb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-52.377525.json,1790753813.337132,1 -v2anneal_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,77.08299423656761,0.012023549948663925,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b4ba980feb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-52.377525.json,1790753813.337132,1 -v2anneal_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.17473937242232,0.018337327275287713,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3b0b6168c6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-47.815235.json,1790753808.876035,1 -v2anneal_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6193414709192107,0.0043278450263979015,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3b0b6168c6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-47.815235.json,1790753808.876035,1 -v2anneal_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17786653227988966,0.0053029115808458155,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3b0b6168c6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-47.815235.json,1790753808.876035,1 -v2anneal_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.110179132974906,0.013139944364727785,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3b0b6168c6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-47.815235.json,1790753808.876035,1 -v2anneal_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.349104803521925,0.019042909231896915,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/70f0c7e40a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.593362.json,1790754273.459884,1 -v2anneal_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7066995473671138,0.003913616363495782,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/70f0c7e40a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.593362.json,1790754273.459884,1 -v2anneal_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28830613821384016,0.0063257109752187235,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/70f0c7e40a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.593362.json,1790754273.459884,1 -v2anneal_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.73913800805703,0.012457942992051394,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/70f0c7e40a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.593362.json,1790754273.459884,1 -v2anneal_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.21869532030526,0.0175252982576263,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/ec80d80200/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-20.084321.json,1790787200.9536,1 -v2anneal_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6187592391521614,0.004213656299728107,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/ec80d80200/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-20.084321.json,1790787200.9536,1 -v2anneal_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16995904516366717,0.005063041263274251,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/ec80d80200/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-20.084321.json,1790787200.9536,1 -v2anneal_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.29114647402319,0.012577953659595478,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/ec80d80200/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-20.084321.json,1790787200.9536,1 -v2anneal_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,52.00089721650374,0.019399392702108224,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/00ea46eb0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-10.345941.json,1790755931.208219,1 -v2anneal_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7524614877953264,0.003988664429173594,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/00ea46eb0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-10.345941.json,1790755931.208219,1 -v2anneal_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.35354027067683375,0.007157678913034543,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/00ea46eb0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-10.345941.json,1790755931.208219,1 -v2anneal_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.3076890531731,0.013002092492689734,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/00ea46eb0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-10.345941.json,1790755931.208219,1 -v2anneal_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.415448183003896,0.019662488850688956,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e79fc27b90/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-13.318153.json,1790753954.177926,1 -v2anneal_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7183554478197022,0.004097515757901205,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e79fc27b90/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-13.318153.json,1790753954.177926,1 -v2anneal_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2948686121058862,0.006672858842154563,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e79fc27b90/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-13.318153.json,1790753954.177926,1 -v2anneal_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.85905872630244,0.012809926967357348,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e79fc27b90/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-13.318153.json,1790753954.177926,1 -v2anneal_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,42.466944407812726,0.020187081169940307,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/9d3106478f/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.359152.json,1790754273.151954,1 -v2anneal_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6871946715569748,0.004341919330422303,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/9d3106478f/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.359152.json,1790754273.151954,1 -v2anneal_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.25361003896952355,0.00662926336834648,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/9d3106478f/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.359152.json,1790754273.151954,1 -v2anneal_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.727902794223,0.013246147333933095,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/9d3106478f/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.359152.json,1790754273.151954,1 -v2anneal_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.93461567643493,0.01858152274925595,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71cb1ce53b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-35.137126.json,1790753795.979147,1 -v2anneal_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6633840609848662,0.004160689602858843,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71cb1ce53b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-35.137126.json,1790753795.979147,1 -v2anneal_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2208823740130061,0.005847959377797158,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71cb1ce53b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-35.137126.json,1790753795.979147,1 -v2anneal_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.50392791957384,0.012887467585880915,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71cb1ce53b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-35.137126.json,1790753795.979147,1 -v2anneal_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.23816885212473,0.020107078397231862,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2853a3f529/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-29.880964.json,1790754030.703189,1 -v2anneal_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6304025758975572,0.00403919699369454,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2853a3f529/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-29.880964.json,1790754030.703189,1 -v2anneal_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17734774212435073,0.005154646229857466,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2853a3f529/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-29.880964.json,1790754030.703189,1 -v2anneal_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.94323414950996,0.012481021207891081,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2853a3f529/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-29.880964.json,1790754030.703189,1 -v2anneal_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.72656745997428,0.018729165013152037,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/528c74883b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-50.378710.json,1790753811.172747,1 -v2anneal_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7195120437941914,0.003979877050855355,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/528c74883b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-50.378710.json,1790753811.172747,1 -v2anneal_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2968650587735023,0.006527073797296061,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/528c74883b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-50.378710.json,1790753811.172747,1 -v2anneal_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.81378353396836,0.012176049238225501,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/528c74883b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-50.378710.json,1790753811.172747,1 -v2anneal_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,51.18553784123636,0.01893545572462668,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/054294ab0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.528825.json,1790753809.373516,1 -v2anneal_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7435431882688878,0.0038234365027966155,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/054294ab0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.528825.json,1790753809.373516,1 -v2anneal_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3373195296045636,0.006868678808483843,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/054294ab0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.528825.json,1790753809.373516,1 -v2anneal_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,71.11038887260742,0.012458973744682682,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/054294ab0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.528825.json,1790753809.373516,1 -v2anneal_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.39504446568901,0.01916167862275869,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e1f506c2f7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-46.808392.json,1790754287.653603,1 -v2anneal_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6747213409005948,0.004259018784201489,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e1f506c2f7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-46.808392.json,1790754287.653603,1 -v2anneal_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2376778277724055,0.006369364686400821,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e1f506c2f7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-46.808392.json,1790754287.653603,1 -v2anneal_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.52640030426099,0.013556580797381404,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e1f506c2f7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-46.808392.json,1790754287.653603,1 -v2anneal_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.00412025410181,0.01879270580214464,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/eb217d5a5e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-37.715744.json,1790754278.530243,1 -v2anneal_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6926183355255301,0.004151670938866643,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/eb217d5a5e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-37.715744.json,1790754278.530243,1 -v2anneal_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.25807757180096513,0.006350528828525068,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/eb217d5a5e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-37.715744.json,1790754278.530243,1 -v2anneal_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.61785547888566,0.012943099097793665,1012,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/eb217d5a5e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-37.715744.json,1790754278.530243,1 -v2anneal_120k,global_mgsm_ca,5,lm-eval,vllm,,exact_match,flexible-extract,0.38,0.030760116042626028,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_cs,5,lm-eval,vllm,,exact_match,flexible-extract,0.34,0.030020073605457907,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.344,0.03010450339231639,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_el,5,lm-eval,vllm,,exact_match,flexible-extract,0.356,0.03034368065715322,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.344,0.03010450339231639,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.372,0.03063032594455832,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_eu,5,lm-eval,vllm,,exact_match,flexible-extract,0.292,0.028814320402205648,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.328,0.029752391824475387,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_gl,5,lm-eval,vllm,,exact_match,flexible-extract,0.352,0.030266288057359945,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_hu,5,lm-eval,vllm,,exact_match,flexible-extract,0.284,0.028576958730437405,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mgsm_sr,5,lm-eval,vllm,,exact_match,flexible-extract,0.348,0.030186568464511704,250,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 -v2anneal_120k,global_mmlu_full_cs,5,lm-eval,vllm,yes,acc,none,0.6697051702036747,0.003752870796175007,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_abstract_algebra,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_anatomy,5,lm-eval,vllm,,acc,none,0.5777777777777777,0.042667634040995855,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_astronomy,5,lm-eval,vllm,,acc,none,0.7697368421052632,0.03426059424403165,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7245283018867924,0.027495663683724022,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_college_biology,5,lm-eval,vllm,,acc,none,0.8263888888888888,0.03167473383795719,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7531914893617021,0.02818544130123409,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6620689655172414,0.03941707632064884,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6534391534391535,0.024508777521028414,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_formal_logic,5,lm-eval,vllm,,acc,none,0.5952380952380952,0.043902592653775656,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_biology,5,lm-eval,vllm,,acc,none,0.8161290322580645,0.022037217340267787,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_geography,5,lm-eval,vllm,,acc,none,0.8282828282828283,0.02686971618742987,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7384615384615385,0.0222821412042044,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4444444444444444,0.030296771286067326,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7857142857142857,0.026653531596715505,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8678899082568807,0.014517801914598314,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.031919234456861886,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8607594936708861,0.022535526352692684,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_human_aging,5,lm-eval,vllm,,acc,none,0.7399103139013453,0.029442495585857424,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_human_sexuality,5,lm-eval,vllm,,acc,none,0.8244274809160306,0.03336820338476075,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_humanities,5,lm-eval,vllm,yes,acc,none,0.5980871413390011,0.006662487628381383,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7423312883435583,0.03436150827846915,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_machine_learning,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_marketing,5,lm-eval,vllm,,acc,none,0.8504273504273504,0.023365051491753757,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_miscellaneous,5,lm-eval,vllm,,acc,none,0.7816091954022989,0.014774358319934516,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_moral_disputes,5,lm-eval,vllm,,acc,none,0.708092485549133,0.02447699407624737,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_moral_scenarios,5,lm-eval,vllm,,acc,none,0.33519553072625696,0.015788007190185846,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_nutrition,5,lm-eval,vllm,,acc,none,0.7581699346405228,0.024518195641879306,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_other,5,lm-eval,vllm,yes,acc,none,0.6977792082394593,0.007947565658089746,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_prehistory,5,lm-eval,vllm,,acc,none,0.7808641975308642,0.02301670564026216,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_professional_accounting,5,lm-eval,vllm,,acc,none,0.44680851063829785,0.02965823509766695,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_professional_law,5,lm-eval,vllm,,acc,none,0.5013037809647979,0.012770192691057138,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_professional_medicine,5,lm-eval,vllm,,acc,none,0.6911764705882353,0.028064998167040053,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_professional_psychology,5,lm-eval,vllm,,acc,none,0.6977124183006536,0.018579232711113967,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_security_studies,5,lm-eval,vllm,,acc,none,0.7673469387755102,0.02704925791589615,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7773805654858629,0.007335920570851386,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_stem,5,lm-eval,vllm,yes,acc,none,0.6438312718046305,0.008241246303279116,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_cs_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 -v2anneal_120k,global_mmlu_full_de,5,lm-eval,vllm,yes,acc,none,0.6719128329297821,0.003756987827625916,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_abstract_algebra,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_anatomy,5,lm-eval,vllm,,acc,none,0.5777777777777777,0.042667634040995855,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_business_ethics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.720754716981132,0.027611163402399694,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_college_biology,5,lm-eval,vllm,,acc,none,0.7708333333333334,0.03514697467862389,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_college_chemistry,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_college_computer_science,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_college_medicine,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.03435568056047877,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7319148936170212,0.028957342788342354,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_econometrics,5,lm-eval,vllm,,acc,none,0.5526315789473685,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6413793103448275,0.03996629574876715,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6084656084656085,0.025138091388851137,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_formal_logic,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.043435254289490965,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_biology,5,lm-eval,vllm,,acc,none,0.8258064516129032,0.02157624818451461,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6305418719211823,0.03395970381998578,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9222797927461139,0.01932180555722318,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7410256410256411,0.02221110681006163,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8277310924369747,0.024528664971305403,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_physics,5,lm-eval,vllm,,acc,none,0.5298013245033113,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8532110091743119,0.015173141845126333,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6481481481481481,0.032568505702936484,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8185654008438819,0.025085961144579647,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_human_aging,5,lm-eval,vllm,,acc,none,0.672645739910314,0.0314938467099413,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_human_sexuality,5,lm-eval,vllm,,acc,none,0.816793893129771,0.03392770926494735,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_humanities,5,lm-eval,vllm,yes,acc,none,0.6004250797024442,0.006680709954633325,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_international_law,5,lm-eval,vllm,,acc,none,0.7768595041322314,0.038007544752287334,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_jurisprudence,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.04414343666854928,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_marketing,5,lm-eval,vllm,,acc,none,0.8846153846153846,0.0209301931851793,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_miscellaneous,5,lm-eval,vllm,,acc,none,0.7905491698595147,0.014551310568143733,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3541899441340782,0.015995644947299357,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_nutrition,5,lm-eval,vllm,,acc,none,0.7450980392156863,0.024954184324879967,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_other,5,lm-eval,vllm,yes,acc,none,0.7048599935629224,0.007905274748860942,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_philosophy,5,lm-eval,vllm,,acc,none,0.7459807073954984,0.024723861504771655,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_prehistory,5,lm-eval,vllm,,acc,none,0.7932098765432098,0.022535006705942877,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_professional_accounting,5,lm-eval,vllm,,acc,none,0.4787234042553192,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_professional_law,5,lm-eval,vllm,,acc,none,0.49282920469361147,0.012768922739553434,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_professional_medicine,5,lm-eval,vllm,,acc,none,0.6801470588235294,0.028332959514031246,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_professional_psychology,5,lm-eval,vllm,,acc,none,0.704248366013072,0.01846315413263271,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_security_studies,5,lm-eval,vllm,,acc,none,0.7306122448979592,0.028401252029022956,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7812804679883003,0.007312855340974806,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_sociology,5,lm-eval,vllm,,acc,none,0.845771144278607,0.025538433368578303,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_stem,5,lm-eval,vllm,yes,acc,none,0.6393910561370124,0.008304461499253036,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_virology,5,lm-eval,vllm,,acc,none,0.5301204819277109,0.03885425420866771,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_de_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 -v2anneal_120k,global_mmlu_full_el,5,lm-eval,vllm,yes,acc,none,0.6526135878080046,0.0038343385914138793,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_abstract_algebra,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_astronomy,5,lm-eval,vllm,,acc,none,0.756578947368421,0.03492349668884235,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_business_ethics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_college_biology,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.0389907368735733,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_college_medicine,5,lm-eval,vllm,,acc,none,0.6994219653179191,0.03496101481191176,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7361702127659574,0.028809989854102946,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6243386243386243,0.02494236893115981,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_formal_logic,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.044444444444444446,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_global_facts,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_biology,5,lm-eval,vllm,,acc,none,0.8161290322580645,0.022037217340267787,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.034139638059062394,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_geography,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.02747960301053882,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7538461538461538,0.02184086699042312,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.42592592592592593,0.0301491356013659,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8067226890756303,0.02564947026588922,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_physics,5,lm-eval,vllm,,acc,none,0.543046357615894,0.0406732517424744,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8036697247706422,0.017030719339154426,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.031919234456861886,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.02675640153807894,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_human_aging,5,lm-eval,vllm,,acc,none,0.7085201793721974,0.03050028317654591,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_humanities,5,lm-eval,vllm,yes,acc,none,0.5895855472901169,0.006749299116578611,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_jurisprudence,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.040774947092526284,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_machine_learning,5,lm-eval,vllm,,acc,none,0.5446428571428571,0.04726835553719097,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_marketing,5,lm-eval,vllm,,acc,none,0.8418803418803419,0.02390232554956044,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_medical_genetics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_miscellaneous,5,lm-eval,vllm,,acc,none,0.7100893997445722,0.016225017944770968,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_moral_disputes,5,lm-eval,vllm,,acc,none,0.7254335260115607,0.02402774515526503,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_moral_scenarios,5,lm-eval,vllm,,acc,none,0.358659217877095,0.016040454426164447,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_nutrition,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.025646863097137932,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_other,5,lm-eval,vllm,yes,acc,none,0.6610878661087866,0.008243426337481107,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_prehistory,5,lm-eval,vllm,,acc,none,0.7160493827160493,0.02508947852376511,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_professional_accounting,5,lm-eval,vllm,,acc,none,0.4326241134751773,0.029555454236778834,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_professional_law,5,lm-eval,vllm,,acc,none,0.4863102998696219,0.012765448722610156,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_professional_medicine,5,lm-eval,vllm,,acc,none,0.6286764705882353,0.029349803139765818,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_professional_psychology,5,lm-eval,vllm,,acc,none,0.6911764705882353,0.01869085027359537,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7647058823529411,0.007528408892687631,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_sociology,5,lm-eval,vllm,,acc,none,0.8308457711442786,0.026508590656233278,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_stem,5,lm-eval,vllm,yes,acc,none,0.6289248334919124,0.008379142404051347,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_virology,5,lm-eval,vllm,,acc,none,0.46987951807228917,0.038854254208667706,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_el_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 -v2anneal_120k,global_mmlu_full_en,5,lm-eval,vllm,yes,acc,none,0.72746047571571,0.003597219764774364,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_abstract_algebra,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_anatomy,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.0417165416135454,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_business_ethics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7584905660377359,0.02634148037111831,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_college_biology,5,lm-eval,vllm,,acc,none,0.8611111111111112,0.028919802956134912,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_college_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_college_mathematics,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_computer_security,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7957446808510639,0.02635515841334947,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_econometrics,5,lm-eval,vllm,,acc,none,0.6140350877192983,0.04579639422070431,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7379310344827587,0.03664666337225255,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6402116402116402,0.024718075944129204,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_formal_logic,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.042639068927951274,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_global_facts,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_biology,5,lm-eval,vllm,,acc,none,0.8741935483870967,0.018865834288030025,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6798029556650246,0.032826493853041455,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.027998073798781685,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_geography,5,lm-eval,vllm,,acc,none,0.8939393939393939,0.02193804773885311,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9585492227979274,0.01438543285747641,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.782051282051282,0.020932445774463234,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5148148148148148,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8823529411764706,0.020928472557788826,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_physics,5,lm-eval,vllm,,acc,none,0.5695364238410596,0.04042809961395634,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_psychology,5,lm-eval,vllm,,acc,none,0.9137614678899083,0.012035597300116307,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.03167468706828983,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8725490196078431,0.02340553048084634,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8818565400843882,0.021011052659878477,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_human_aging,5,lm-eval,vllm,,acc,none,0.7802690582959642,0.027790177064383567,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_human_sexuality,5,lm-eval,vllm,,acc,none,0.8473282442748091,0.031545216720054704,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_humanities,5,lm-eval,vllm,yes,acc,none,0.6820403825717322,0.006506514984965544,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_jurisprudence,5,lm-eval,vllm,,acc,none,0.8240740740740741,0.036809181416738786,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7914110429447853,0.03192193448934723,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_machine_learning,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.045479609997643805,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_marketing,5,lm-eval,vllm,,acc,none,0.8931623931623932,0.02023714900899092,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_miscellaneous,5,lm-eval,vllm,,acc,none,0.8250319284802043,0.01358661921990341,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_moral_disputes,5,lm-eval,vllm,,acc,none,0.8005780346820809,0.02151190065425248,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5363128491620112,0.01667834189453305,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_nutrition,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.02428861946604616,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_other,5,lm-eval,vllm,yes,acc,none,0.7415513356935951,0.007613923104461062,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_philosophy,5,lm-eval,vllm,,acc,none,0.7620578778135049,0.02418515064781868,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_prehistory,5,lm-eval,vllm,,acc,none,0.8395061728395061,0.02042395535477805,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_professional_accounting,5,lm-eval,vllm,,acc,none,0.5319148936170213,0.02976667507587383,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_professional_law,5,lm-eval,vllm,,acc,none,0.5691003911342895,0.01264769588954738,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_professional_medicine,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.026799562024887664,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_professional_psychology,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.017555818091322294,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_public_relations,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.04350271442923247,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8280792980175495,0.006643628608638319,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_sociology,5,lm-eval,vllm,,acc,none,0.8805970149253731,0.022928793277219726,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_stem,5,lm-eval,vllm,yes,acc,none,0.6831588962892483,0.008003661378727453,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_virology,5,lm-eval,vllm,,acc,none,0.5481927710843374,0.0387437155658795,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_en_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 -v2anneal_120k,global_mmlu_full_es,5,lm-eval,vllm,yes,acc,none,0.6874376869391825,0.003728818484984839,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_anatomy,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.04292596718256977,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7056603773584905,0.028049186315695293,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_college_biology,5,lm-eval,vllm,,acc,none,0.8194444444444444,0.03216600808802272,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_college_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7489361702127659,0.02834696377716252,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_econometrics,5,lm-eval,vllm,,acc,none,0.6228070175438597,0.0455952214195822,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6375661375661376,0.024757473902752066,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_formal_logic,5,lm-eval,vllm,,acc,none,0.626984126984127,0.043255060420170875,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_global_facts,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_biology,5,lm-eval,vllm,,acc,none,0.8483870967741935,0.020402616654416734,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6748768472906403,0.03295797566311267,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_geography,5,lm-eval,vllm,,acc,none,0.8434343434343434,0.025890520358141458,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8756476683937824,0.02381447708659357,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7871794871794872,0.020752423722128037,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48148148148148145,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8361344537815126,0.024044054940440488,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_physics,5,lm-eval,vllm,,acc,none,0.543046357615894,0.0406732517424744,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8715596330275229,0.014344977542914248,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8607594936708861,0.022535526352692684,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_human_aging,5,lm-eval,vllm,,acc,none,0.7219730941704036,0.030069584874494053,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_humanities,5,lm-eval,vllm,yes,acc,none,0.620403825717322,0.006686733429319939,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_jurisprudence,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.04414343666854928,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_machine_learning,5,lm-eval,vllm,,acc,none,0.5625,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_marketing,5,lm-eval,vllm,,acc,none,0.8717948717948718,0.021901905115073377,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_miscellaneous,5,lm-eval,vllm,,acc,none,0.7982120051085568,0.014351702181636911,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_moral_disputes,5,lm-eval,vllm,,acc,none,0.7601156069364162,0.02298959254312351,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_moral_scenarios,5,lm-eval,vllm,,acc,none,0.423463687150838,0.016525425898773562,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_nutrition,5,lm-eval,vllm,,acc,none,0.7287581699346405,0.025457756696667815,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_other,5,lm-eval,vllm,yes,acc,none,0.7064692629546186,0.007937951875125856,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_philosophy,5,lm-eval,vllm,,acc,none,0.7491961414790996,0.024619771956697113,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_prehistory,5,lm-eval,vllm,,acc,none,0.7654320987654321,0.0235768817440057,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_professional_accounting,5,lm-eval,vllm,,acc,none,0.5212765957446809,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_professional_law,5,lm-eval,vllm,,acc,none,0.500651890482399,0.012770225252255563,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_professional_medicine,5,lm-eval,vllm,,acc,none,0.6838235294117647,0.028245687391462857,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_professional_psychology,5,lm-eval,vllm,,acc,none,0.7369281045751634,0.01781267654232072,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8007799805004875,0.007119363215298641,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_stem,5,lm-eval,vllm,yes,acc,none,0.6581033935934031,0.008170378681286278,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_virology,5,lm-eval,vllm,,acc,none,0.5240963855421686,0.03887971849597267,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_es_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 -v2anneal_120k,global_mmlu_full_fr,5,lm-eval,vllm,yes,acc,none,0.6817404928072924,0.003730267366728688,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_anatomy,5,lm-eval,vllm,,acc,none,0.5851851851851851,0.04256193767901412,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7622641509433963,0.026199808807561956,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_college_physics,5,lm-eval,vllm,,acc,none,0.45098039215686275,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7659574468085106,0.02767845257821238,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_econometrics,5,lm-eval,vllm,,acc,none,0.5701754385964912,0.04657047260594963,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.024796060602699895,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_global_facts,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.625615763546798,0.03405155380561957,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8131313131313131,0.02777253333421894,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.735897435897436,0.02235219373745328,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4962962962962963,0.030484701665084435,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7983193277310925,0.026064313406304485,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5827814569536424,0.040261414976346124,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8440366972477065,0.015555802713590066,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03214952147802747,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.024857478080250486,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8734177215189873,0.021644195727955198,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_human_aging,5,lm-eval,vllm,,acc,none,0.7174887892376681,0.030216831011508755,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_human_sexuality,5,lm-eval,vllm,,acc,none,0.816793893129771,0.03392770926494735,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_humanities,5,lm-eval,vllm,yes,acc,none,0.6153028692879915,0.006589471865302478,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_international_law,5,lm-eval,vllm,,acc,none,0.8677685950413223,0.030922788320445795,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.04019107472557348,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7177914110429447,0.03536117886664741,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_marketing,5,lm-eval,vllm,,acc,none,0.8717948717948718,0.021901905115073377,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_miscellaneous,5,lm-eval,vllm,,acc,none,0.8058748403575989,0.014143970276657597,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7745664739884393,0.02249723019096748,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.35083798882681566,0.0159610366752309,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_nutrition,5,lm-eval,vllm,,acc,none,0.7450980392156863,0.024954184324879967,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_other,5,lm-eval,vllm,yes,acc,none,0.7196652719665272,0.007801703442256751,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_prehistory,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.02277971908873342,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_professional_accounting,5,lm-eval,vllm,,acc,none,0.5035460992907801,0.029826749153280853,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_professional_law,5,lm-eval,vllm,,acc,none,0.5143415906127771,0.012764981829524309,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_professional_medicine,5,lm-eval,vllm,,acc,none,0.7169117647058824,0.027365861131513815,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.01863559403442406,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7747806304842378,0.007423231266373894,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_stem,5,lm-eval,vllm,yes,acc,none,0.6527117031398668,0.00822941700385638,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_fr_world_religions,5,lm-eval,vllm,,acc,none,0.8304093567251462,0.02878210810540169,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 -v2anneal_120k,global_mmlu_full_it,5,lm-eval,vllm,yes,acc,none,0.682025352513887,0.0037583299201274737,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_abstract_algebra,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_astronomy,5,lm-eval,vllm,,acc,none,0.7828947368421053,0.03355045304882924,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7169811320754716,0.027724236492700883,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_college_computer_science,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_college_medicine,5,lm-eval,vllm,,acc,none,0.6820809248554913,0.0355068398916558,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_college_physics,5,lm-eval,vllm,,acc,none,0.5686274509803921,0.049280995972875316,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7787234042553192,0.027136349602424097,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7034482758620689,0.03806142687309988,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.024552292209342713,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_biology,5,lm-eval,vllm,,acc,none,0.8516129032258064,0.02022273755433042,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7818181818181819,0.032250781083062896,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_geography,5,lm-eval,vllm,,acc,none,0.8585858585858586,0.024825909793343353,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9119170984455959,0.020453746601601056,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7461538461538462,0.022066054378726312,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4777777777777778,0.030455413985678415,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8109243697478992,0.025435119438105305,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8642201834862385,0.014686907556339952,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6712962962962963,0.03203614084670054,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8227848101265823,0.024856364184503203,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_human_aging,5,lm-eval,vllm,,acc,none,0.6905829596412556,0.031024411740572237,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_humanities,5,lm-eval,vllm,yes,acc,none,0.6195536663124336,0.006723637844478757,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_logical_fallacies,5,lm-eval,vllm,,acc,none,0.754601226993865,0.033809398139433525,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_machine_learning,5,lm-eval,vllm,,acc,none,0.5892857142857143,0.04669510663875191,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_miscellaneous,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.014866821664709668,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_moral_scenarios,5,lm-eval,vllm,,acc,none,0.42681564245810055,0.01654240195463199,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_nutrition,5,lm-eval,vllm,,acc,none,0.7287581699346405,0.025457756696667815,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_other,5,lm-eval,vllm,yes,acc,none,0.6926295461860316,0.008023291631135028,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_philosophy,5,lm-eval,vllm,,acc,none,0.729903536977492,0.02521804037341055,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_prehistory,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.02346842983245111,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_professional_accounting,5,lm-eval,vllm,,acc,none,0.4645390070921986,0.029752389657427127,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_professional_law,5,lm-eval,vllm,,acc,none,0.5058670143415906,0.012769356925216389,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_professional_medicine,5,lm-eval,vllm,,acc,none,0.6727941176470589,0.028501452860396626,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_professional_psychology,5,lm-eval,vllm,,acc,none,0.7124183006535948,0.018311653053648198,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_security_studies,5,lm-eval,vllm,,acc,none,0.7387755102040816,0.028123429335142832,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7855053623659408,0.007261510331206792,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_sociology,5,lm-eval,vllm,,acc,none,0.8507462686567164,0.02519692987482706,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_stem,5,lm-eval,vllm,yes,acc,none,0.6638122423089121,0.008170950843446854,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_it_world_religions,5,lm-eval,vllm,,acc,none,0.8304093567251462,0.02878210810540169,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 -v2anneal_120k,global_mmlu_full_lt,5,lm-eval,vllm,yes,acc,none,0.6447087309500071,0.003834954661258017,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_anatomy,5,lm-eval,vllm,,acc,none,0.5481481481481482,0.04299268905480864,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_business_ethics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6830188679245283,0.02863723563980094,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_college_biology,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.037455547914624555,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_college_medicine,5,lm-eval,vllm,,acc,none,0.653179190751445,0.03629146670159661,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.723404255319149,0.0292418838696288,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6344827586206897,0.04013124195424389,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.02487081525105711,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_formal_logic,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04426266681379905,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8193548387096774,0.021886178567172513,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6108374384236454,0.03430462416103873,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7696969696969697,0.03287666758603482,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026552207828215258,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6846153846153846,0.023559646983189894,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.42592592592592593,0.0301491356013659,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.027553614467863825,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_physics,5,lm-eval,vllm,,acc,none,0.5364238410596026,0.04071636065944211,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8385321100917431,0.01577623925616323,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7941176470588235,0.028379449451588684,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_human_aging,5,lm-eval,vllm,,acc,none,0.695067264573991,0.03089861088247754,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_humanities,5,lm-eval,vllm,yes,acc,none,0.5706695005313497,0.006727393801655137,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6441717791411042,0.03761521380046734,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7254150702426565,0.015959829933084018,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.02454761779480379,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.30726256983240224,0.015430158846469541,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_nutrition,5,lm-eval,vllm,,acc,none,0.696078431372549,0.026336613469046647,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_other,5,lm-eval,vllm,yes,acc,none,0.6655938204055359,0.008253937102695764,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_prehistory,5,lm-eval,vllm,,acc,none,0.7376543209876543,0.024477222856135194,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_professional_accounting,5,lm-eval,vllm,,acc,none,0.4397163120567376,0.029609912075594054,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_professional_law,5,lm-eval,vllm,,acc,none,0.4706649282920469,0.012748238397365576,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6801470588235294,0.028332959514031246,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_professional_psychology,5,lm-eval,vllm,,acc,none,0.6699346405228758,0.019023726160724508,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7539811504712383,0.00760907636224509,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_stem,5,lm-eval,vllm,yes,acc,none,0.6279733587059942,0.008344418627947905,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_virology,5,lm-eval,vllm,,acc,none,0.5240963855421686,0.03887971849597267,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_lt_world_religions,5,lm-eval,vllm,,acc,none,0.8011695906432749,0.030611116557432514,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 -v2anneal_120k,global_mmlu_full_nl,5,lm-eval,vllm,yes,acc,none,0.6798176897877796,0.0037771316110996704,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_college_biology,5,lm-eval,vllm,,acc,none,0.8263888888888888,0.03167473383795719,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_college_medicine,5,lm-eval,vllm,,acc,none,0.6820809248554913,0.0355068398916558,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7489361702127659,0.02834696377716252,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6534391534391535,0.024508777521028414,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8387096774193549,0.020923327006423326,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6157635467980296,0.03422398565657553,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8383838383838383,0.02622591986362927,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9222797927461139,0.01932180555722318,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7564102564102564,0.021763733684173926,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4740740740740741,0.030444528528810785,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8678899082568807,0.014517801914598314,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.03114144782353603,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.024857478080250486,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_human_aging,5,lm-eval,vllm,,acc,none,0.726457399103139,0.029918586707798872,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_human_sexuality,5,lm-eval,vllm,,acc,none,0.8244274809160306,0.03336820338476075,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_humanities,5,lm-eval,vllm,yes,acc,none,0.6242295430393199,0.006743691932231002,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_jurisprudence,5,lm-eval,vllm,,acc,none,0.8055555555555556,0.038260763248848646,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7300613496932515,0.034878251684978955,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_machine_learning,5,lm-eval,vllm,,acc,none,0.6160714285714286,0.04616143075028549,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_medical_genetics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7624521072796935,0.015218733046150228,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.024257901705323326,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.48156424581005586,0.016711130497782726,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_other,5,lm-eval,vllm,yes,acc,none,0.6874798841326037,0.008072337219895169,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_philosophy,5,lm-eval,vllm,,acc,none,0.7363344051446945,0.02502553850053229,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_prehistory,5,lm-eval,vllm,,acc,none,0.7716049382716049,0.02335821184062624,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_professional_accounting,5,lm-eval,vllm,,acc,none,0.45390070921985815,0.029700453247291494,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_professional_law,5,lm-eval,vllm,,acc,none,0.49478487614080835,0.012769541449652715,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6507352941176471,0.02895975519682485,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.01863559403442406,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_security_studies,5,lm-eval,vllm,,acc,none,0.7591836734693878,0.027372942201788125,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7819304517387066,0.007296650035422438,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_stem,5,lm-eval,vllm,yes,acc,none,0.6555661274976213,0.008229245464897578,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_virology,5,lm-eval,vllm,,acc,none,0.536144578313253,0.038823108508905954,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_nl_world_religions,5,lm-eval,vllm,,acc,none,0.7953216374269005,0.03094445977853322,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 -v2anneal_120k,global_mmlu_full_pl,5,lm-eval,vllm,yes,acc,none,0.6667141432844325,0.003799249241086684,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_anatomy,5,lm-eval,vllm,,acc,none,0.5259259259259259,0.043135316967505756,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_astronomy,5,lm-eval,vllm,,acc,none,0.75,0.03523807393012047,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_college_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7148936170212766,0.029513196625539355,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_econometrics,5,lm-eval,vllm,,acc,none,0.5175438596491229,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7034482758620689,0.03806142687309988,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.02467786284133279,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_global_facts,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8161290322580645,0.022037217340267787,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6502463054187192,0.033554009049695604,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.030117688929503603,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.02747960301053882,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7487179487179487,0.021992016662370557,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45185185185185184,0.030343862998512657,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7815126050420168,0.026841514322958934,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8550458715596331,0.015094215699700396,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6712962962962963,0.03203614084670054,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8578431372549019,0.024509803921568627,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8438818565400844,0.02362715946031866,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_human_aging,5,lm-eval,vllm,,acc,none,0.6816143497757847,0.03126580522513711,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_humanities,5,lm-eval,vllm,yes,acc,none,0.6091392136025505,0.006722798551955746,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7407407407407407,0.04236511258094632,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7055214723926381,0.03581165790474083,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_machine_learning,5,lm-eval,vllm,,acc,none,0.5089285714285714,0.04745033255489126,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_marketing,5,lm-eval,vllm,,acc,none,0.8632478632478633,0.022509033937077844,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_medical_genetics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7522349936143039,0.01543808308056889,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7254335260115607,0.02402774515526503,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.41675977653631285,0.016489134962438902,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_nutrition,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.025261691219729484,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_other,5,lm-eval,vllm,yes,acc,none,0.6800772449308015,0.00810505359029553,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_philosophy,5,lm-eval,vllm,,acc,none,0.7170418006430869,0.025583062489984907,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_prehistory,5,lm-eval,vllm,,acc,none,0.7438271604938271,0.02428853363772609,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_professional_accounting,5,lm-eval,vllm,,acc,none,0.41134751773049644,0.02935491115994096,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_professional_law,5,lm-eval,vllm,,acc,none,0.4869621903520209,0.01276589388383549,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6727941176470589,0.028501452860396626,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6813725490196079,0.018850084696468674,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_security_studies,5,lm-eval,vllm,,acc,none,0.8204081632653061,0.024573293589585647,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7731556711082223,0.007412902985589852,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_stem,5,lm-eval,vllm,yes,acc,none,0.6355851569933397,0.008338602379348973,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pl_world_religions,5,lm-eval,vllm,,acc,none,0.847953216374269,0.027539122889061483,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 -v2anneal_120k,global_mmlu_full_pt,5,lm-eval,vllm,yes,acc,none,0.682025352513887,0.0037448204298812723,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7396226415094339,0.027008766090708045,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_college_chemistry,5,lm-eval,vllm,,acc,none,0.55,0.05,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_computer_security,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7446808510638298,0.0285048564705142,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6137566137566137,0.02507598176760173,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_formal_logic,5,lm-eval,vllm,,acc,none,0.626984126984127,0.043255060420170875,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8354838709677419,0.021090847745939306,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6650246305418719,0.03320852742348313,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8434343434343434,0.025890520358141458,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9119170984455959,0.020453746601601056,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7384615384615385,0.0222821412042044,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45555555555555555,0.03036486250482447,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7899159663865546,0.026461398717471864,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_physics,5,lm-eval,vllm,,acc,none,0.543046357615894,0.0406732517424744,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8715596330275229,0.014344977542914248,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6620370370370371,0.03225941352631297,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8480392156862745,0.025195658428931827,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8312236286919831,0.02438140683258622,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7862595419847328,0.03595461611774691,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_humanities,5,lm-eval,vllm,yes,acc,none,0.6172157279489905,0.0066998555277832175,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_jurisprudence,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.038935425188248496,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7361963190184049,0.03462419931615622,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_machine_learning,5,lm-eval,vllm,,acc,none,0.5625,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_management,5,lm-eval,vllm,,acc,none,0.8349514563106796,0.03675668832233187,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7867177522349936,0.014648172749593532,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.41899441340782123,0.016501579306861677,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_nutrition,5,lm-eval,vllm,,acc,none,0.7418300653594772,0.025058503316958167,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_other,5,lm-eval,vllm,yes,acc,none,0.7064692629546186,0.007917212960405633,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_prehistory,5,lm-eval,vllm,,acc,none,0.7654320987654321,0.0235768817440057,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_professional_accounting,5,lm-eval,vllm,,acc,none,0.4716312056737589,0.029779450957303062,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_professional_law,5,lm-eval,vllm,,acc,none,0.4980443285528031,0.012770138422208597,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_professional_medicine,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.027678468642144703,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_professional_psychology,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.01791797406959478,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_public_relations,5,lm-eval,vllm,,acc,none,0.7,0.04389311454644288,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_security_studies,5,lm-eval,vllm,,acc,none,0.7877551020408163,0.026176967197866795,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7897302567435814,0.0072320848578294955,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_stem,5,lm-eval,vllm,yes,acc,none,0.6495401205201395,0.008216767377945324,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_virology,5,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_pt_world_religions,5,lm-eval,vllm,,acc,none,0.8011695906432749,0.030611116557432514,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 -v2anneal_120k,global_mmlu_full_ro,5,lm-eval,vllm,yes,acc,none,0.6792479703745905,0.0037628876442344036,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_abstract_algebra,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_astronomy,5,lm-eval,vllm,,acc,none,0.7697368421052632,0.03426059424403165,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_business_ethics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7245283018867924,0.027495663683724022,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_college_biology,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03476590104304133,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7276595744680852,0.029101290698386736,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_econometrics,5,lm-eval,vllm,,acc,none,0.5087719298245614,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7241379310344828,0.037245636197746325,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.02487081525105711,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_biology,5,lm-eval,vllm,,acc,none,0.8483870967741935,0.020402616654416734,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6108374384236454,0.03430462416103873,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_geography,5,lm-eval,vllm,,acc,none,0.8232323232323232,0.027178752639044908,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9015544041450777,0.021500249576033463,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.764102564102564,0.02152596540740865,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4740740740740741,0.030444528528810785,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8487394957983193,0.02327425589870791,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_physics,5,lm-eval,vllm,,acc,none,0.5364238410596026,0.04071636065944211,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8477064220183487,0.015405084393157036,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6620370370370371,0.03225941352631297,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8438818565400844,0.02362715946031866,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_human_aging,5,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_humanities,5,lm-eval,vllm,yes,acc,none,0.620616365568544,0.006693979365863609,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_machine_learning,5,lm-eval,vllm,,acc,none,0.48214285714285715,0.047427623612430116,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_management,5,lm-eval,vllm,,acc,none,0.7961165048543689,0.0398913985953177,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_marketing,5,lm-eval,vllm,,acc,none,0.8931623931623932,0.02023714900899092,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_miscellaneous,5,lm-eval,vllm,,acc,none,0.7739463601532567,0.014957458504335842,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_moral_scenarios,5,lm-eval,vllm,,acc,none,0.41787709497206704,0.01649540063582002,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_other,5,lm-eval,vllm,yes,acc,none,0.7013196009011908,0.007949403879882092,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_philosophy,5,lm-eval,vllm,,acc,none,0.7395498392282959,0.0249267232248456,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_prehistory,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.02277971908873342,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_professional_accounting,5,lm-eval,vllm,,acc,none,0.4787234042553192,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_professional_law,5,lm-eval,vllm,,acc,none,0.5078226857887875,0.012768673076111898,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_professional_medicine,5,lm-eval,vllm,,acc,none,0.6838235294117647,0.028245687391462857,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_professional_psychology,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.01843342764940195,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_public_relations,5,lm-eval,vllm,,acc,none,0.7,0.04389311454644288,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_security_studies,5,lm-eval,vllm,,acc,none,0.7551020408163265,0.02752963744017492,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7816054598635034,0.007316777985487735,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_sociology,5,lm-eval,vllm,,acc,none,0.8258706467661692,0.026814951200421624,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_stem,5,lm-eval,vllm,yes,acc,none,0.6450999048525214,0.008289382940293891,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_ro_world_religions,5,lm-eval,vllm,,acc,none,0.8011695906432749,0.030611116557432514,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 -v2anneal_120k,global_mmlu_full_sr,5,lm-eval,vllm,yes,acc,none,0.6487679817689788,0.003871306185785417,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_anatomy,5,lm-eval,vllm,,acc,none,0.562962962962963,0.042849586397534056,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_business_ethics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6754716981132075,0.02881561571343209,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_college_biology,5,lm-eval,vllm,,acc,none,0.7361111111111112,0.036856510958975304,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_college_medicine,5,lm-eval,vllm,,acc,none,0.6763005780346821,0.03567603799639168,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_computer_security,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7021276595744681,0.029896145682095487,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_econometrics,5,lm-eval,vllm,,acc,none,0.47368421052631576,0.046970851366478654,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6137931034482759,0.04057324734419032,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6693121693121693,0.02422996529842509,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8258064516129032,0.02157624818451461,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5566502463054187,0.03495334582162933,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7878787878787878,0.031922715695482946,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7929292929292929,0.02886977846026699,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8601036269430051,0.025033870583015143,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6974358974358974,0.02329088805377271,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.44814814814814813,0.030321167196316254,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.027553614467863825,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5099337748344371,0.040816771072484305,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8348623853211009,0.015919557829976096,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6435185185185185,0.03266478331527272,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.869198312236287,0.02194876605947081,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_human_aging,5,lm-eval,vllm,,acc,none,0.6636771300448431,0.031708824268455046,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_humanities,5,lm-eval,vllm,yes,acc,none,0.5934112646121148,0.006835846738958121,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_jurisprudence,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.044531975073749855,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6748466257668712,0.036803503712864595,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_medical_genetics,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_miscellaneous,5,lm-eval,vllm,,acc,none,0.6934865900383141,0.016486952893041595,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7196531791907514,0.024182427496577626,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4547486033519553,0.016653875777524,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_nutrition,5,lm-eval,vllm,,acc,none,0.7124183006535948,0.025917806117147137,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_other,5,lm-eval,vllm,yes,acc,none,0.6578693273253943,0.008305556685220664,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_philosophy,5,lm-eval,vllm,,acc,none,0.7106109324758842,0.02575586592263286,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_prehistory,5,lm-eval,vllm,,acc,none,0.6790123456790124,0.025976566010862776,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_professional_accounting,5,lm-eval,vllm,,acc,none,0.44680851063829785,0.02965823509766695,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_professional_law,5,lm-eval,vllm,,acc,none,0.4602346805736636,0.012729785386598602,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6507352941176471,0.02895975519682485,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6699346405228758,0.019023726160724508,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7468313292167695,0.007700641677115095,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_stem,5,lm-eval,vllm,yes,acc,none,0.6267047256581034,0.008351092933103703,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sr_world_religions,5,lm-eval,vllm,,acc,none,0.7485380116959064,0.03327504423846844,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 -v2anneal_120k,global_mmlu_full_sv,5,lm-eval,vllm,yes,acc,none,0.6803161942743199,0.003756574953417373,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_anatomy,5,lm-eval,vllm,,acc,none,0.6444444444444445,0.04135176749720385,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_astronomy,5,lm-eval,vllm,,acc,none,0.8157894736842105,0.031546980450822305,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_business_ethics,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7471698113207547,0.02674989977124118,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_college_biology,5,lm-eval,vllm,,acc,none,0.7916666666666666,0.03396116205845331,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_college_medicine,5,lm-eval,vllm,,acc,none,0.6994219653179191,0.03496101481191176,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_college_physics,5,lm-eval,vllm,,acc,none,0.45098039215686275,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_conceptual_physics,5,lm-eval,vllm,,acc,none,0.723404255319149,0.0292418838696288,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_econometrics,5,lm-eval,vllm,,acc,none,0.5526315789473685,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.656084656084656,0.0244644266255964,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_formal_logic,5,lm-eval,vllm,,acc,none,0.5952380952380952,0.043902592653775656,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6157635467980296,0.03422398565657553,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_geography,5,lm-eval,vllm,,acc,none,0.8838383838383839,0.02282888177524936,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8808290155440415,0.02338193534812143,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7538461538461538,0.02184086699042312,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4703703703703704,0.030431963547936577,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7983193277310925,0.026064313406304485,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8825688073394495,0.013802780227377303,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03214952147802747,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8480392156862745,0.025195658428931827,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_humanities,5,lm-eval,vllm,yes,acc,none,0.6255047821466525,0.006723551555825562,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_machine_learning,5,lm-eval,vllm,,acc,none,0.4732142857142857,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_marketing,5,lm-eval,vllm,,acc,none,0.9017094017094017,0.019503444900757564,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_medical_genetics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_miscellaneous,5,lm-eval,vllm,,acc,none,0.7624521072796935,0.015218733046150228,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_moral_disputes,5,lm-eval,vllm,,acc,none,0.7485549132947977,0.023357365785874006,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4592178770949721,0.016666783616525672,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_nutrition,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.024630048979824716,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_other,5,lm-eval,vllm,yes,acc,none,0.6948825233344061,0.00794694035183702,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_philosophy,5,lm-eval,vllm,,acc,none,0.7266881028938906,0.025311765975426094,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_prehistory,5,lm-eval,vllm,,acc,none,0.7901234567901234,0.022658344085981406,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_professional_accounting,5,lm-eval,vllm,,acc,none,0.4432624113475177,0.02963483847376595,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_professional_law,5,lm-eval,vllm,,acc,none,0.5058670143415906,0.012769356925216389,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_professional_medicine,5,lm-eval,vllm,,acc,none,0.6544117647058824,0.0288881931039887,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_professional_psychology,5,lm-eval,vllm,,acc,none,0.6977124183006536,0.018579232711113967,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_social_sciences,5,lm-eval,vllm,yes,acc,none,0.785830354241144,0.007248688817717436,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_stem,5,lm-eval,vllm,yes,acc,none,0.6447827465905487,0.008238247215245341,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_sv_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 -v2anneal_120k,global_mmlu_full_tr,5,lm-eval,vllm,yes,acc,none,0.6360205098988748,0.003866952876590305,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_college_biology,5,lm-eval,vllm,,acc,none,0.7430555555555556,0.03653946969442102,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_college_computer_science,5,lm-eval,vllm,,acc,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_college_medicine,5,lm-eval,vllm,,acc,none,0.6416184971098265,0.0365634365335316,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.676595744680851,0.03057944277361037,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6413793103448275,0.03996629574876715,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6137566137566137,0.02507598176760173,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_formal_logic,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.043435254289490965,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_global_facts,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_biology,5,lm-eval,vllm,,acc,none,0.7935483870967742,0.023025899617188667,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6108374384236454,0.03430462416103873,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7212121212121212,0.03501438706296781,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7929292929292929,0.02886977846026699,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.772020725388601,0.030276909945178256,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6948717948717948,0.02334633529332588,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45185185185185184,0.030343862998512657,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7478991596638656,0.02820554503327774,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8422018348623853,0.015630022970092496,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.625,0.033016908987210894,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8284313725490197,0.026460569561240675,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_human_aging,5,lm-eval,vllm,,acc,none,0.6681614349775785,0.03160295143776678,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_humanities,5,lm-eval,vllm,yes,acc,none,0.5666312433581296,0.006733571872640295,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_jurisprudence,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.044531975073749855,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6748466257668712,0.036803503712864595,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_machine_learning,5,lm-eval,vllm,,acc,none,0.5357142857142857,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_medical_genetics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7330779054916986,0.015818450894777576,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.02454761779480379,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.29832402234636873,0.015301840045129371,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_nutrition,5,lm-eval,vllm,,acc,none,0.6895424836601307,0.026493033225145922,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_other,5,lm-eval,vllm,yes,acc,none,0.664306404892179,0.008250330437027453,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_philosophy,5,lm-eval,vllm,,acc,none,0.707395498392283,0.02583989833487794,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_prehistory,5,lm-eval,vllm,,acc,none,0.7160493827160493,0.02508947852376511,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_professional_accounting,5,lm-eval,vllm,,acc,none,0.4645390070921986,0.029752389657427127,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_professional_law,5,lm-eval,vllm,,acc,none,0.46936114732724904,0.012746237711716587,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6397058823529411,0.02916312857067069,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6470588235294118,0.019333142020797084,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_security_studies,5,lm-eval,vllm,,acc,none,0.746938775510204,0.027833023871399704,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.734481637959051,0.007831469203283299,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_sociology,5,lm-eval,vllm,,acc,none,0.7860696517412935,0.028996909693328965,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_stem,5,lm-eval,vllm,yes,acc,none,0.615604186489058,0.008433375768968663,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_tr_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 -v2anneal_120k,global_mmlu_full_uk,5,lm-eval,vllm,yes,acc,none,0.6465603190428714,0.0038462323193176806,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_abstract_algebra,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_anatomy,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.04292596718256977,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_college_biology,5,lm-eval,vllm,,acc,none,0.7291666666666666,0.03716177437566019,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_college_computer_science,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_college_medicine,5,lm-eval,vllm,,acc,none,0.6936416184971098,0.035149425512674394,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7319148936170212,0.028957342788342354,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_econometrics,5,lm-eval,vllm,,acc,none,0.47368421052631576,0.046970851366478654,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.040434618619167494,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6455026455026455,0.024636830602842035,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_biology,5,lm-eval,vllm,,acc,none,0.8096774193548387,0.02233170761182313,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6009852216748769,0.03445487686264716,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_geography,5,lm-eval,vllm,,acc,none,0.8131313131313131,0.02777253333421894,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.717948717948718,0.02281581309889655,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.43703703703703706,0.030242862397654047,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7899159663865546,0.026461398717471864,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_physics,5,lm-eval,vllm,,acc,none,0.4966887417218543,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8403669724770643,0.015703498348461794,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6620370370370371,0.03225941352631297,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.02675640153807894,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8016877637130801,0.02595502084162111,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_human_aging,5,lm-eval,vllm,,acc,none,0.7040358744394619,0.03063659134869978,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_human_sexuality,5,lm-eval,vllm,,acc,none,0.7709923664122137,0.036853466317118506,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_humanities,5,lm-eval,vllm,yes,acc,none,0.5774707757704569,0.006797581752806713,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6809815950920245,0.03661997551073836,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_medical_genetics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_miscellaneous,5,lm-eval,vllm,,acc,none,0.6947637292464879,0.016467711947635053,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_moral_disputes,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.02378620325550823,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_moral_scenarios,5,lm-eval,vllm,,acc,none,0.35195530726256985,0.015972668523689174,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_nutrition,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.025360603796242578,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_other,5,lm-eval,vllm,yes,acc,none,0.6652719665271967,0.008234543068386576,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_philosophy,5,lm-eval,vllm,,acc,none,0.6945337620578779,0.026160584450140488,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_prehistory,5,lm-eval,vllm,,acc,none,0.691358024691358,0.025702640260603798,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_professional_accounting,5,lm-eval,vllm,,acc,none,0.4219858156028369,0.029462189233370586,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_professional_law,5,lm-eval,vllm,,acc,none,0.47522816166883963,0.012754553719781769,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_professional_medicine,5,lm-eval,vllm,,acc,none,0.6580882352941176,0.02881472242225415,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_professional_psychology,5,lm-eval,vllm,,acc,none,0.6437908496732027,0.01937333242072444,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7536561585960351,0.007593986532701041,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_stem,5,lm-eval,vllm,yes,acc,none,0.6267047256581034,0.008352252974326808,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_mmlu_full_uk_world_religions,5,lm-eval,vllm,,acc,none,0.7426900584795322,0.03352799844161867,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 -v2anneal_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2742a66b0_2026-09-30T07-34-23.323292.json,1790753498.250096,1 -v2anneal_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2742a66b0_2026-09-30T07-34-23.323292.json,1790753498.250096,1 -v2anneal_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_norm,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2742a66b0_2026-09-30T07-34-23.323292.json,1790753498.250096,1 -v2anneal_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/79b292dc6b_2026-09-30T07-38-28.423728.json,1790753749.2418041,1 -v2anneal_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/79b292dc6b_2026-09-30T07-38-28.423728.json,1790753749.2418041,1 -v2anneal_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_norm,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/79b292dc6b_2026-09-30T07-38-28.423728.json,1790753749.2418041,1 -v2anneal_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/63b3a0b294_2026-09-30T07-44-31.920137.json,1790754113.915074,1 -v2anneal_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/63b3a0b294_2026-09-30T07-44-31.920137.json,1790754113.915074,1 -v2anneal_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/63b3a0b294_2026-09-30T07-44-31.920137.json,1790754113.915074,1 -v2anneal_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4924bbb6d0_2026-09-30T08-14-13.642642.json,1790755618.6044626,1 -v2anneal_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4924bbb6d0_2026-09-30T08-14-13.642642.json,1790755618.6044626,1 -v2anneal_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4924bbb6d0_2026-09-30T08-14-13.642642.json,1790755618.6044626,1 -v2anneal_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/840820d405_2026-09-30T08-21-06.214459.json,1790756304.2545533,1 -v2anneal_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_bytes,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/840820d405_2026-09-30T08-21-06.214459.json,1790756304.2545533,1 -v2anneal_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/840820d405_2026-09-30T08-21-06.214459.json,1790756304.2545533,1 -v2anneal_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/833f7e32e8_2026-09-30T07-44-44.398421.json,1790754119.8761442,1 -v2anneal_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/833f7e32e8_2026-09-30T07-44-44.398421.json,1790754119.8761442,1 -v2anneal_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_norm,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/833f7e32e8_2026-09-30T07-44-44.398421.json,1790754119.8761442,1 -v2anneal_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bfe6bbf2d5_2026-09-30T07-34-09.656418.json,1790753469.4275866,1 -v2anneal_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bfe6bbf2d5_2026-09-30T07-34-09.656418.json,1790753469.4275866,1 -v2anneal_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_norm,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bfe6bbf2d5_2026-09-30T07-34-09.656418.json,1790753469.4275866,1 -v2anneal_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/80121a87ef_2026-09-30T08-26-12.160155.json,1790756609.7753644,1 -v2anneal_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_bytes,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/80121a87ef_2026-09-30T08-26-12.160155.json,1790756609.7753644,1 -v2anneal_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_norm,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/80121a87ef_2026-09-30T08-26-12.160155.json,1790756609.7753644,1 -v2anneal_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c5671f1b3f_2026-09-30T07-44-42.287808.json,1790754113.237653,1 -v2anneal_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c5671f1b3f_2026-09-30T07-44-42.287808.json,1790754113.237653,1 -v2anneal_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c5671f1b3f_2026-09-30T07-44-42.287808.json,1790754113.237653,1 -v2anneal_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5ceebe7d29_2026-09-30T08-22-50.495124.json,1790756402.4216914,1 -v2anneal_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5ceebe7d29_2026-09-30T08-22-50.495124.json,1790756402.4216914,1 -v2anneal_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5ceebe7d29_2026-09-30T08-22-50.495124.json,1790756402.4216914,1 -v2anneal_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/36e0bc56df_2026-09-30T08-14-09.446609.json,1790755619.031715,1 -v2anneal_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/36e0bc56df_2026-09-30T08-14-09.446609.json,1790755619.031715,1 -v2anneal_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/36e0bc56df_2026-09-30T08-14-09.446609.json,1790755619.031715,1 -v2anneal_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c68f87c76_2026-09-30T07-34-34.064015.json,1790753514.0559473,1 -v2anneal_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_bytes,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c68f87c76_2026-09-30T07-34-34.064015.json,1790753514.0559473,1 -v2anneal_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c68f87c76_2026-09-30T07-34-34.064015.json,1790753514.0559473,1 -v2anneal_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/91be30ef53_2026-09-30T08-25-53.461396.json,1790756521.8708394,1 -v2anneal_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/91be30ef53_2026-09-30T08-25-53.461396.json,1790756521.8708394,1 -v2anneal_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/91be30ef53_2026-09-30T08-25-53.461396.json,1790756521.8708394,1 -v2anneal_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2ad0f947e_2026-09-30T08-52-13.524323.json,1790758110.2966776,1 -v2anneal_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2ad0f947e_2026-09-30T08-52-13.524323.json,1790758110.2966776,1 -v2anneal_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2ad0f947e_2026-09-30T08-52-13.524323.json,1790758110.2966776,1 -v2anneal_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2873c7e9bd_2026-09-30T08-16-52.509147.json,1790756045.7483003,1 -v2anneal_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_bytes,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2873c7e9bd_2026-09-30T08-16-52.509147.json,1790756045.7483003,1 -v2anneal_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_norm,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2873c7e9bd_2026-09-30T08-16-52.509147.json,1790756045.7483003,1 -v2anneal_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e045906d60_2026-09-30T08-32-53.241466.json,1790757010.362059,1 -v2anneal_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e045906d60_2026-09-30T08-32-53.241466.json,1790757010.362059,1 -v2anneal_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e045906d60_2026-09-30T08-32-53.241466.json,1790757010.362059,1 -v2anneal_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e37413d4b7_2026-09-30T07-40-27.169106.json,1790753865.9279923,1 -v2anneal_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_bytes,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e37413d4b7_2026-09-30T07-40-27.169106.json,1790753865.9279923,1 -v2anneal_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_norm,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e37413d4b7_2026-09-30T07-40-27.169106.json,1790753865.9279923,1 -v2anneal_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f9d8d59099_2026-09-30T08-20-24.847155.json,1790756204.7786026,1 -v2anneal_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f9d8d59099_2026-09-30T08-20-24.847155.json,1790756204.7786026,1 -v2anneal_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f9d8d59099_2026-09-30T08-20-24.847155.json,1790756204.7786026,1 -v2anneal_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/234af93d20_2026-09-30T07-34-49.187877.json,1790753515.1355681,1 -v2anneal_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/234af93d20_2026-09-30T07-34-49.187877.json,1790753515.1355681,1 -v2anneal_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/234af93d20_2026-09-30T07-34-49.187877.json,1790753515.1355681,1 -v2anneal_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a9550c2bc6_2026-09-30T08-27-03.489027.json,1790756654.9120932,1 -v2anneal_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a9550c2bc6_2026-09-30T08-27-03.489027.json,1790756654.9120932,1 -v2anneal_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a9550c2bc6_2026-09-30T08-27-03.489027.json,1790756654.9120932,1 -v2anneal_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3fc3097adc_2026-09-30T08-37-26.610842.json,1790757281.022396,1 -v2anneal_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3fc3097adc_2026-09-30T08-37-26.610842.json,1790757281.022396,1 -v2anneal_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3fc3097adc_2026-09-30T08-37-26.610842.json,1790757281.022396,1 -v2anneal_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26fc6af8dc_2026-09-30T08-21-07.787343.json,1790756304.2311845,1 -v2anneal_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26fc6af8dc_2026-09-30T08-21-07.787343.json,1790756304.2311845,1 -v2anneal_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_norm,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26fc6af8dc_2026-09-30T08-21-07.787343.json,1790756304.2311845,1 -v2anneal_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c307e7852_2026-09-30T08-49-20.957848.json,1790757995.5064917,1 -v2anneal_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c307e7852_2026-09-30T08-49-20.957848.json,1790757995.5064917,1 -v2anneal_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c307e7852_2026-09-30T08-49-20.957848.json,1790757995.5064917,1 -v2anneal_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/783959f5af_2026-09-30T08-31-36.390910.json,1790756931.2110164,1 -v2anneal_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/783959f5af_2026-09-30T08-31-36.390910.json,1790756931.2110164,1 -v2anneal_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/783959f5af_2026-09-30T08-31-36.390910.json,1790756931.2110164,1 -v2anneal_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac5b1660b8_2026-09-30T07-44-36.170496.json,1790754112.5478299,1 -v2anneal_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac5b1660b8_2026-09-30T07-44-36.170496.json,1790754112.5478299,1 -v2anneal_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac5b1660b8_2026-09-30T07-44-36.170496.json,1790754112.5478299,1 -v2anneal_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d8d456e8e4_2026-09-30T08-26-55.313880.json,1790756651.919656,1 -v2anneal_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_bytes,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d8d456e8e4_2026-09-30T08-26-55.313880.json,1790756651.919656,1 -v2anneal_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d8d456e8e4_2026-09-30T08-26-55.313880.json,1790756651.919656,1 -v2anneal_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0fb76307f4_2026-09-30T08-45-19.823966.json,1790757747.1804583,1 -v2anneal_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0fb76307f4_2026-09-30T08-45-19.823966.json,1790757747.1804583,1 -v2anneal_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0fb76307f4_2026-09-30T08-45-19.823966.json,1790757747.1804583,1 -v2anneal_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e87f450629_2026-09-30T08-37-23.640945.json,1790757281.1401832,1 -v2anneal_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e87f450629_2026-09-30T08-37-23.640945.json,1790757281.1401832,1 -v2anneal_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e87f450629_2026-09-30T08-37-23.640945.json,1790757281.1401832,1 -v2anneal_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/08d9322aec_2026-09-30T08-32-47.881271.json,1790757007.1889896,1 -v2anneal_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.93,0.02564323999762428,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/08d9322aec_2026-09-30T08-32-47.881271.json,1790757007.1889896,1 -v2anneal_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_norm,none,0.92,0.027265992434429072,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/08d9322aec_2026-09-30T08-32-47.881271.json,1790757007.1889896,1 -v2anneal_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b1174b183c_2026-09-30T07-34-14.320040.json,1790753469.507396,1 -v2anneal_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b1174b183c_2026-09-30T07-34-14.320040.json,1790753469.507396,1 -v2anneal_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b1174b183c_2026-09-30T07-34-14.320040.json,1790753469.507396,1 -v2anneal_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7975a755a_2026-09-30T08-37-25.920039.json,1790757281.045539,1 -v2anneal_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_bytes,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7975a755a_2026-09-30T08-37-25.920039.json,1790757281.045539,1 -v2anneal_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7975a755a_2026-09-30T08-37-25.920039.json,1790757281.045539,1 -v2anneal_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2efb68c3c2_2026-09-30T16-51-06.383456.json,1790786895.427406,1 -v2anneal_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2efb68c3c2_2026-09-30T16-51-06.383456.json,1790786895.427406,1 -v2anneal_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2efb68c3c2_2026-09-30T16-51-06.383456.json,1790786895.427406,1 -v2anneal_120k,global_piqa_prompted_als_latn,0,lm-eval,vllm,,exact_match,strict_match,0.34,0.04760952285695236,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bce375b22e_2026-09-30T07-44-39.749531.json,1790754112.5746913,1 -v2anneal_120k,global_piqa_prompted_bos_latn,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.049236596391733084,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/397d20115f_2026-09-30T08-32-30.461657.json,1790756982.7556195,1 -v2anneal_120k,global_piqa_prompted_bul_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.04960449637488584,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0d0ec9daf5_2026-09-30T08-31-38.029932.json,1790756929.0569682,1 -v2anneal_120k,global_piqa_prompted_cat_latn,0,lm-eval,vllm,,exact_match,strict_match,0.35,0.0479372485441102,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b61d215beb_2026-09-30T08-17-05.136081.json,1790756056.6785228,1 -v2anneal_120k,global_piqa_prompted_ces_latn,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.04975698519562428,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b76070c117_2026-09-30T08-17-00.354385.json,1790756044.61594,1 -v2anneal_120k,global_piqa_prompted_deu_latn,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.04975698519562428,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/816a5ebf6d_2026-09-30T08-14-19.042858.json,1790755619.446754,1 -v2anneal_120k,global_piqa_prompted_ekk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.3,0.046056618647183814,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f78975ae0d_2026-09-30T08-20-35.025463.json,1790756205.077248,1 -v2anneal_120k,global_piqa_prompted_ell_grek,0,lm-eval,vllm,,exact_match,strict_match,0.29,0.04560480215720684,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2632646f17_2026-09-30T08-11-16.655166.json,1790754237.150687,1 -v2anneal_120k,global_piqa_prompted_eng_latn,0,lm-eval,vllm,,exact_match,strict_match,0.37,0.048523658709391,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6e13c58851_2026-09-30T07-34-39.424026.json,1790753513.6044145,1 -v2anneal_120k,global_piqa_prompted_fin_latn,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.04923659639173309,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3b13b7f09a_2026-09-30T08-49-22.072597.json,1790757994.81424,1 -v2anneal_120k,global_piqa_prompted_fra_latn_fran,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620333,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a67103a8e7_2026-09-30T08-31-36.052166.json,1790756930.3454416,1 -v2anneal_120k,global_piqa_prompted_glg_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.049431107042371025,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/154a5175e5_2026-09-30T08-49-21.047257.json,1790757994.7078502,1 -v2anneal_120k,global_piqa_prompted_hrv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.05,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78dae58ed1_2026-09-30T08-14-17.059858.json,1790755619.4818902,1 -v2anneal_120k,global_piqa_prompted_hun_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/97f17d1f74_2026-09-30T07-34-31.586580.json,1790753469.1640487,1 -v2anneal_120k,global_piqa_prompted_isl_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0cd0de4218_2026-09-30T08-26-18.870606.json,1790756611.5903957,1 -v2anneal_120k,global_piqa_prompted_ita_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0a473b0b3_2026-09-30T08-14-13.923744.json,1790755618.9056883,1 -v2anneal_120k,global_piqa_prompted_kat_geor,0,lm-eval,vllm,,exact_match,strict_match,0.07,0.025643239997624283,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4057deaf42_2026-09-30T08-39-19.627576.json,1790757385.491713,1 -v2anneal_120k,global_piqa_prompted_lit_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.05,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6c34a0db15_2026-09-30T08-11-17.172019.json,1790754233.995834,1 -v2anneal_120k,global_piqa_prompted_mkd_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.37,0.04852365870939099,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f6a3af5284_2026-09-30T07-38-38.432820.json,1790753750.9444952,1 -v2anneal_120k,global_piqa_prompted_nld_latn,0,lm-eval,vllm,,exact_match,strict_match,0.32,0.04688261722621505,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0663bf9606_2026-09-30T08-27-04.898330.json,1790756653.1883855,1 -v2anneal_120k,global_piqa_prompted_nno_latn,0,lm-eval,vllm,,exact_match,strict_match,0.44,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7ee2c0e759_2026-09-30T08-48-48.910029.json,1790757959.9045625,1 -v2anneal_120k,global_piqa_prompted_nob_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001975,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fc62bfca31_2026-09-30T08-41-43.627119.json,1790757467.6409137,1 -v2anneal_120k,global_piqa_prompted_pol_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001974,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f9384a211c_2026-09-30T08-37-30.021810.json,1790757280.8220496,1 -v2anneal_120k,global_piqa_prompted_por_latn_port,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ae5e793fdd_2026-09-30T07-34-39.919773.json,1790753498.2306492,1 -v2anneal_120k,global_piqa_prompted_ron_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.04943110704237102,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/712e8221d4_2026-09-30T08-22-52.255002.json,1790756406.0055506,1 -v2anneal_120k,global_piqa_prompted_slk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c05610e62_2026-09-30T08-14-15.511790.json,1790755618.0235023,1 -v2anneal_120k,global_piqa_prompted_slv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9e0f52e9c6_2026-09-30T08-43-38.901126.json,1790757647.7072637,1 -v2anneal_120k,global_piqa_prompted_spa_latn_spai,0,lm-eval,vllm,,exact_match,strict_match,0.48,0.050211673156867795,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/461c6d7d3b_2026-09-30T08-52-51.632329.json,1790758208.568163,1 -v2anneal_120k,global_piqa_prompted_srp_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.04923659639173309,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/58414f4b03_2026-09-30T07-34-48.980088.json,1790753513.601634,1 -v2anneal_120k,global_piqa_prompted_swe_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/47d929537c_2026-09-30T08-47-30.821358.json,1790757887.3143518,1 -v2anneal_120k,global_piqa_prompted_tur_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001975,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/45525e4a60_2026-09-30T08-31-32.830931.json,1790756929.319447,1 -v2anneal_120k,global_piqa_prompted_ukr_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7706f2b918_2026-09-30T08-33-22.276808.json,1790757024.090673,1 -v2anneal_120k,gsm8k,4,lm-eval,vllm,,exact_match,flexible-extract,0.8248673237300985,0.010469307043157896,1319,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/df7559c0a8_2026-09-30T08-12-00.352428.json,1790754224.8933513,1 -v2anneal_120k,gsm8k,4,lm-eval,vllm,,exact_match,strict-match,0.8218347232752085,0.010540132527549465,1319,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/df7559c0a8_2026-09-30T08-12-00.352428.json,1790754224.8933513,1 -v2anneal_120k,hellaswag,0,lm-eval,vllm,,acc,none,0.6094403505277833,0.004868787333436616,10042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/90ed463fa8_2026-09-30T08-15-38.767205.json,1790755619.2456968,1 -v2anneal_120k,hellaswag,0,lm-eval,vllm,,acc_norm,none,0.8001394144592711,0.003990781278700381,10042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/90ed463fa8_2026-09-30T08-15-38.767205.json,1790755619.2456968,1 -v2anneal_120k,hellaswag,10,lm-eval,vllm,,acc,none,0.632244572794264,0.004812088620277034,10042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/62aeb64f3a_2026-09-30T08-16-16.383565.json,1790754118.4044855,1 -v2anneal_120k,hellaswag,10,lm-eval,vllm,,acc_norm,none,0.8301135232025493,0.0037476555337545773,10042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/62aeb64f3a_2026-09-30T08-16-16.383565.json,1790754118.4044855,1 -v2anneal_120k,hellaswag_ca,0,lm-eval,vllm,,acc,none,0.5085224188470308,0.005209272701845509,9211,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7cf016755_2026-09-30T08-28-15.172504.json,1790756644.8667934,1 -v2anneal_120k,hellaswag_ca,0,lm-eval,vllm,,acc_norm,none,0.6670285528172837,0.004910728162964033,9211,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7cf016755_2026-09-30T08-28-15.172504.json,1790756644.8667934,1 -v2anneal_120k,hellaswag_da,0,lm-eval,vllm,,acc,none,0.538527673293928,0.00516823190899877,9305,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed8f84f0c5_2026-09-30T08-15-41.449503.json,1790755619.3633385,1 -v2anneal_120k,hellaswag_da,0,lm-eval,vllm,,acc_norm,none,0.6967221923696937,0.004765574762726751,9305,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed8f84f0c5_2026-09-30T08-15-41.449503.json,1790755619.3633385,1 -v2anneal_120k,hellaswag_de,0,lm-eval,vllm,,acc,none,0.5308497011101623,0.005156339773239881,9368,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d433c1f584_2026-09-30T07-42-05.796758.json,1790753873.5420372,1 -v2anneal_120k,hellaswag_de,0,lm-eval,vllm,,acc_norm,none,0.6891545687446626,0.004782228287116277,9368,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d433c1f584_2026-09-30T07-42-05.796758.json,1790753873.5420372,1 -v2anneal_120k,hellaswag_es,0,lm-eval,vllm,,acc,none,0.5648602517601877,0.005120891534898503,9374,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9b1d836ba5_2026-09-30T08-54-52.399325.json,1790758235.158873,1 -v2anneal_120k,hellaswag_es,0,lm-eval,vllm,,acc_norm,none,0.7402389588222744,0.004529326922991129,9374,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9b1d836ba5_2026-09-30T08-54-52.399325.json,1790758235.158873,1 -v2anneal_120k,hellaswag_eu,0,lm-eval,vllm,,acc,none,0.29983792544570503,0.004762969779745698,9255,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/cdd651a216_2026-09-30T08-16-40.989334.json,1790755924.982935,1 -v2anneal_120k,hellaswag_eu,0,lm-eval,vllm,,acc_norm,none,0.36175040518638574,0.004994994788213977,9255,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/cdd651a216_2026-09-30T08-16-40.989334.json,1790755924.982935,1 -v2anneal_120k,hellaswag_fr,0,lm-eval,vllm,,acc,none,0.5541871921182266,0.005143998502778556,9338,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9dc5b2b749_2026-09-30T08-46-54.343751.json,1790757746.2377396,1 -v2anneal_120k,hellaswag_fr,0,lm-eval,vllm,,acc_norm,none,0.7255300920968087,0.004618185824360283,9338,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9dc5b2b749_2026-09-30T08-46-54.343751.json,1790757746.2377396,1 -v2anneal_120k,hellaswag_hr,0,lm-eval,vllm,,acc,none,0.4960405448210326,0.005137849721301563,9471,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b055b2ebcc_2026-09-30T08-22-34.981676.json,1790756304.2756293,1 -v2anneal_120k,hellaswag_hr,0,lm-eval,vllm,,acc_norm,none,0.6601203674374406,0.004867423638391813,9471,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b055b2ebcc_2026-09-30T08-22-34.981676.json,1790756304.2756293,1 -v2anneal_120k,hellaswag_hu,0,lm-eval,vllm,,acc,none,0.4459918850751179,0.005205611432301113,9119,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/06c8a9ec68_2026-09-30T08-22-46.566573.json,1790756302.5520985,1 -v2anneal_120k,hellaswag_hu,0,lm-eval,vllm,,acc_norm,none,0.5801074679241145,0.0051686069776874085,9119,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/06c8a9ec68_2026-09-30T08-22-46.566573.json,1790756302.5520985,1 -v2anneal_120k,hellaswag_it,0,lm-eval,vllm,,acc,none,0.5344283694115087,0.005202750487887637,9193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e5b097ac29_2026-09-30T08-12-31.103542.json,1790754231.90667,1 -v2anneal_120k,hellaswag_it,0,lm-eval,vllm,,acc_norm,none,0.7060807135864244,0.004751559904731701,9193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e5b097ac29_2026-09-30T08-12-31.103542.json,1790754231.90667,1 -v2anneal_120k,hellaswag_nl,0,lm-eval,vllm,,acc,none,0.5327576902320561,0.005183661951081025,9265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1d5c07a42a_2026-09-30T07-35-34.910569.json,1790753469.3869572,1 -v2anneal_120k,hellaswag_nl,0,lm-eval,vllm,,acc_norm,none,0.6953049109552077,0.00478212696566229,9265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1d5c07a42a_2026-09-30T07-35-34.910569.json,1790753469.3869572,1 -v2anneal_120k,hellaswag_pt,0,lm-eval,vllm,,acc,none,0.5479466897822083,0.005180959385457814,9229,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c222073ef_2026-09-30T08-33-01.288789.json,1790756930.4788506,1 -v2anneal_120k,hellaswag_pt,0,lm-eval,vllm,,acc_norm,none,0.7206631270993608,0.004670641044834582,9229,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c222073ef_2026-09-30T08-33-01.288789.json,1790756930.4788506,1 -v2anneal_120k,hellaswag_ro,0,lm-eval,vllm,,acc,none,0.5163872363439698,0.00519764553349342,9245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d33cf24f4d_2026-09-30T08-22-48.248347.json,1790756304.2128713,1 -v2anneal_120k,hellaswag_ro,0,lm-eval,vllm,,acc_norm,none,0.6697674418604651,0.004891499259185562,9245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d33cf24f4d_2026-09-30T08-22-48.248347.json,1790756304.2128713,1 -v2anneal_120k,hellaswag_sk,0,lm-eval,vllm,,acc,none,0.47221929362150766,0.005126286162723778,9485,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/21e88b8133_2026-09-30T08-15-44.516015.json,1790755619.5046027,1 -v2anneal_120k,hellaswag_sk,0,lm-eval,vllm,,acc_norm,none,0.6133895624670532,0.005000451341117208,9485,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/21e88b8133_2026-09-30T08-15-44.516015.json,1790755619.5046027,1 -v2anneal_120k,hellaswag_sr,0,lm-eval,vllm,,acc,none,0.49857127738385015,0.005143968364677214,9449,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/25189a1c49_2026-09-30T08-28-26.565139.json,1790756648.4586253,1 -v2anneal_120k,hellaswag_sr,0,lm-eval,vllm,,acc_norm,none,0.6534024764525347,0.004895907156155269,9449,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/25189a1c49_2026-09-30T08-28-26.565139.json,1790756648.4586253,1 -v2anneal_120k,hellaswag_sv,0,lm-eval,vllm,,acc,none,0.5310238982679237,0.00522529918123481,9122,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e4d13cb1e6_2026-09-30T07-36-09.835275.json,1790753513.6272507,1 -v2anneal_120k,hellaswag_sv,0,lm-eval,vllm,,acc_norm,none,0.7042315281736461,0.004778729445632501,9122,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e4d13cb1e6_2026-09-30T07-36-09.835275.json,1790753513.6272507,1 -v2anneal_120k,hellaswag_uk,0,lm-eval,vllm,,acc,none,0.4667871187161229,0.005143527822058997,9409,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/99e03c17d8_2026-09-30T08-49-09.803919.json,1790757886.574674,1 -v2anneal_120k,hellaswag_uk,0,lm-eval,vllm,,acc_norm,none,0.6068657668190031,0.005035795633020201,9409,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/99e03c17d8_2026-09-30T08-49-09.803919.json,1790757886.574674,1 -v2anneal_120k,ifeval,0,lm-eval,vllm,,inst_level_loose_acc,none,0.44364508393285373,,541,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69b44d6b54_2026-09-30T07-36-01.976399.json,1790753496.2781277,1 -v2anneal_120k,ifeval,0,lm-eval,vllm,,inst_level_strict_acc,none,0.4184652278177458,,541,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69b44d6b54_2026-09-30T07-36-01.976399.json,1790753496.2781277,1 -v2anneal_120k,ifeval,0,lm-eval,vllm,,prompt_level_loose_acc,none,0.2975970425138632,0.019674812004413393,541,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69b44d6b54_2026-09-30T07-36-01.976399.json,1790753496.2781277,1 -v2anneal_120k,ifeval,0,lm-eval,vllm,,prompt_level_strict_acc,none,0.2735674676524954,0.019183727107392846,541,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69b44d6b54_2026-09-30T07-36-01.976399.json,1790753496.2781277,1 -v2anneal_120k,include_base_44_albanian,0,lm-eval,vllm,yes,acc,none,0.7404718693284936,0.018709782815849715,551,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 -v2anneal_120k,include_base_44_albanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.7488789237668162,0.029105220833224605,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 -v2anneal_120k,include_base_44_albanian_business_commerce,0,lm-eval,vllm,,acc,none,0.726457399103139,0.029918586707798872,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 -v2anneal_120k,include_base_44_albanian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 -v2anneal_120k,include_base_44_albanian_social_science,0,lm-eval,vllm,,acc,none,0.8181818181818182,0.0524863881081478,55,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 -v2anneal_120k,include_base_44_albanian_stem,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 -v2anneal_120k,include_base_44_basque,0,lm-eval,vllm,yes,acc,none,0.456,0.02229623834840707,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d2dbe40f12_2026-09-30T08-47-32.827069.json,1790757888.5945458,1 -v2anneal_120k,include_base_44_basque_professional_certification,0,lm-eval,vllm,,acc,none,0.456,0.02229623834840707,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d2dbe40f12_2026-09-30T08-47-32.827069.json,1790757888.5945458,1 -v2anneal_120k,include_base_44_bulgarian,0,lm-eval,vllm,yes,acc,none,0.6854545454545454,0.01961876977892238,550,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4705518c29_2026-09-30T08-43-29.717376.json,1790757643.804846,1 -v2anneal_120k,include_base_44_bulgarian_arts_humanities,0,lm-eval,vllm,,acc,none,0.76,0.027065293652238982,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4705518c29_2026-09-30T08-43-29.717376.json,1790757643.804846,1 -v2anneal_120k,include_base_44_bulgarian_social_science,0,lm-eval,vllm,,acc,none,0.636,0.030491555220405475,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4705518c29_2026-09-30T08-43-29.717376.json,1790757643.804846,1 -v2anneal_120k,include_base_44_bulgarian_stem,0,lm-eval,vllm,,acc,none,0.56,0.07091242083423346,50,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4705518c29_2026-09-30T08-43-29.717376.json,1790757643.804846,1 -v2anneal_120k,include_base_44_croatian,0,lm-eval,vllm,yes,acc,none,0.7381818181818182,0.0187117067834429,550,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c3d68932e_2026-09-30T08-48-47.341561.json,1790757959.9321353,1 -v2anneal_120k,include_base_44_croatian_arts_humanities,0,lm-eval,vllm,,acc,none,0.7,0.029040893477575786,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c3d68932e_2026-09-30T08-48-47.341561.json,1790757959.9321353,1 -v2anneal_120k,include_base_44_croatian_social_science,0,lm-eval,vllm,,acc,none,0.784,0.02607865766373279,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c3d68932e_2026-09-30T08-48-47.341561.json,1790757959.9321353,1 -v2anneal_120k,include_base_44_croatian_stem,0,lm-eval,vllm,,acc,none,0.7,0.06546536707079771,50,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c3d68932e_2026-09-30T08-48-47.341561.json,1790757959.9321353,1 -v2anneal_120k,include_base_44_dutch,0,lm-eval,vllm,yes,acc,none,0.7096188747731398,0.01928875003389857,551,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 -v2anneal_120k,include_base_44_dutch_applied_science,0,lm-eval,vllm,,acc,none,0.9333333333333333,0.06666666666666665,15,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 -v2anneal_120k,include_base_44_dutch_arts_humanities,0,lm-eval,vllm,,acc,none,0.7325102880658436,0.028454615592677018,243,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 -v2anneal_120k,include_base_44_dutch_health_oriented_education,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 -v2anneal_120k,include_base_44_dutch_social_science,0,lm-eval,vllm,,acc,none,0.6954732510288066,0.029583207218060927,243,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 -v2anneal_120k,include_base_44_dutch_stem,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 -v2anneal_120k,include_base_44_estonian,0,lm-eval,vllm,yes,acc,none,0.5758928571428571,0.0325273790057567,224,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 -v2anneal_120k,include_base_44_estonian_applied_science,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.09705231721239392,14,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 -v2anneal_120k,include_base_44_estonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.515527950310559,0.03950940416210684,161,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 -v2anneal_120k,include_base_44_estonian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5,0.5,2,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 -v2anneal_120k,include_base_44_estonian_social_science,0,lm-eval,vllm,,acc,none,0.5454545454545454,0.1574591643244434,11,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 -v2anneal_120k,include_base_44_estonian_stem,0,lm-eval,vllm,,acc,none,0.75,0.07319250547113999,36,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 -v2anneal_120k,include_base_44_finnish,0,lm-eval,vllm,yes,acc,none,0.5263157894736842,0.02109254822268859,551,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 -v2anneal_120k,include_base_44_finnish_applied_science,0,lm-eval,vllm,,acc,none,0.4482758620689655,0.09398415777506855,29,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 -v2anneal_120k,include_base_44_finnish_arts_humanities,0,lm-eval,vllm,,acc,none,0.4424778761061947,0.03311201227233577,226,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 -v2anneal_120k,include_base_44_finnish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6222222222222222,0.07309112127323451,45,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 -v2anneal_120k,include_base_44_finnish_social_science,0,lm-eval,vllm,,acc,none,0.584070796460177,0.032858761806830256,226,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 -v2anneal_120k,include_base_44_finnish_stem,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 -v2anneal_120k,include_base_44_french,0,lm-eval,vllm,yes,acc,none,0.5871121718377088,0.023751693706955852,419,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 -v2anneal_120k,include_base_44_french_arts_humanities,0,lm-eval,vllm,,acc,none,0.6466165413533834,0.029364565335867333,266,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 -v2anneal_120k,include_base_44_french_driving_license,0,lm-eval,vllm,,acc,none,0.3829787234042553,0.0716734777251339,47,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 -v2anneal_120k,include_base_44_french_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5625,0.128086884574495,16,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 -v2anneal_120k,include_base_44_french_social_science,0,lm-eval,vllm,,acc,none,0.5540540540540541,0.05817759292339765,74,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 -v2anneal_120k,include_base_44_french_stem,0,lm-eval,vllm,,acc,none,0.375,0.125,16,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 -v2anneal_120k,include_base_44_georgian,0,lm-eval,vllm,yes,acc,none,0.47,0.0223427481925028,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/320792eefb_2026-09-30T08-11-18.728761.json,1790754232.3812442,1 -v2anneal_120k,include_base_44_georgian_arts_humanities,0,lm-eval,vllm,,acc,none,0.47,0.0223427481925028,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/320792eefb_2026-09-30T08-11-18.728761.json,1790754232.3812442,1 -v2anneal_120k,include_base_44_german,0,lm-eval,vllm,yes,acc,none,0.5539568345323741,0.04247861636666499,139,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1af60b0859_2026-09-30T08-15-11.795544.json,1790755924.968859,1 -v2anneal_120k,include_base_44_german_driving_license,0,lm-eval,vllm,,acc,none,0.4782608695652174,0.10649955403405124,23,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1af60b0859_2026-09-30T08-15-11.795544.json,1790755924.968859,1 -v2anneal_120k,include_base_44_german_social_science,0,lm-eval,vllm,,acc,none,0.5824175824175825,0.05198368783767558,91,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1af60b0859_2026-09-30T08-15-11.795544.json,1790755924.968859,1 -v2anneal_120k,include_base_44_german_stem,0,lm-eval,vllm,,acc,none,0.52,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1af60b0859_2026-09-30T08-15-11.795544.json,1790755924.968859,1 -v2anneal_120k,include_base_44_greek,0,lm-eval,vllm,yes,acc,none,0.5561594202898551,0.021018339570042663,552,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 -v2anneal_120k,include_base_44_greek_arts_humanities,0,lm-eval,vllm,,acc,none,0.6216216216216216,0.08083044344561424,37,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 -v2anneal_120k,include_base_44_greek_business_commerce,0,lm-eval,vllm,,acc,none,0.7301587301587301,0.05637245937794517,63,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 -v2anneal_120k,include_base_44_greek_health_oriented_education,0,lm-eval,vllm,,acc,none,0.4,0.1,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 -v2anneal_120k,include_base_44_greek_medical_license,0,lm-eval,vllm,,acc,none,0.5298507462686567,0.043278164192160934,134,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 -v2anneal_120k,include_base_44_greek_professional_certification,0,lm-eval,vllm,,acc,none,0.4925373134328358,0.04335066912520509,134,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 -v2anneal_120k,include_base_44_greek_social_science,0,lm-eval,vllm,,acc,none,0.5746268656716418,0.04286987049655245,134,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 -v2anneal_120k,include_base_44_greek_stem,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 -v2anneal_120k,include_base_44_hungarian,0,lm-eval,vllm,yes,acc,none,0.4690909090909091,0.021315519716048476,550,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cabf9c92e_2026-09-30T07-34-11.753188.json,1790753468.5730548,1 -v2anneal_120k,include_base_44_hungarian_applied_science,0,lm-eval,vllm,,acc,none,0.45161290322580644,0.02698903311400244,341,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cabf9c92e_2026-09-30T07-34-11.753188.json,1790753468.5730548,1 -v2anneal_120k,include_base_44_hungarian_social_science,0,lm-eval,vllm,,acc,none,0.5,0.03696106354772864,184,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cabf9c92e_2026-09-30T07-34-11.753188.json,1790753468.5730548,1 -v2anneal_120k,include_base_44_hungarian_stem,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cabf9c92e_2026-09-30T07-34-11.753188.json,1790753468.5730548,1 -v2anneal_120k,include_base_44_italian,0,lm-eval,vllm,yes,acc,none,0.7135036496350365,0.019273755977909514,548,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 -v2anneal_120k,include_base_44_italian_applied_science,0,lm-eval,vllm,,acc,none,0.7714285714285715,0.0720144043214405,35,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 -v2anneal_120k,include_base_44_italian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6706586826347305,0.03647706112341117,167,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 -v2anneal_120k,include_base_44_italian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.75,0.1305582419667734,12,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 -v2anneal_120k,include_base_44_italian_professional_certification,0,lm-eval,vllm,,acc,none,0.6774193548387096,0.03766930374975111,155,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 -v2anneal_120k,include_base_44_italian_social_science,0,lm-eval,vllm,,acc,none,0.7844311377245509,0.031916582528798025,167,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 -v2anneal_120k,include_base_44_italian_stem,0,lm-eval,vllm,,acc,none,0.5833333333333334,0.1486470975026408,12,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 -v2anneal_120k,include_base_44_lithuanian,0,lm-eval,vllm,yes,acc,none,0.6292134831460674,0.020827616929200387,534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 -v2anneal_120k,include_base_44_lithuanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6208955223880597,0.02654700230415632,335,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 -v2anneal_120k,include_base_44_lithuanian_business_commerce,0,lm-eval,vllm,,acc,none,0.5,0.08006407690254357,40,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 -v2anneal_120k,include_base_44_lithuanian_professional_certification,0,lm-eval,vllm,,acc,none,0.6666666666666666,0.0687614164172529,48,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 -v2anneal_120k,include_base_44_lithuanian_social_science,0,lm-eval,vllm,,acc,none,0.6233766233766234,0.055580454819565604,77,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 -v2anneal_120k,include_base_44_lithuanian_stem,0,lm-eval,vllm,,acc,none,0.8235294117647058,0.06636189115503133,34,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 -v2anneal_120k,include_base_44_north macedonian,0,lm-eval,vllm,yes,acc,none,0.8148820326678766,0.016447155294872257,551,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 -v2anneal_120k,include_base_44_north macedonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.023432852220591778,224,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 -v2anneal_120k,include_base_44_north macedonian_business_commerce,0,lm-eval,vllm,,acc,none,0.78125,0.027683220663030285,224,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 -v2anneal_120k,include_base_44_north macedonian_social_science,0,lm-eval,vllm,,acc,none,0.8867924528301887,0.04393868070601046,53,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 -v2anneal_120k,include_base_44_north macedonian_stem,0,lm-eval,vllm,,acc,none,0.7,0.06546536707079771,50,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 -v2anneal_120k,include_base_44_polish,0,lm-eval,vllm,yes,acc,none,0.5109489051094891,0.021320189652018123,548,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fb24c7bd9d_2026-09-30T08-20-34.086249.json,1790756205.4627898,1 -v2anneal_120k,include_base_44_polish_professional_certification,0,lm-eval,vllm,,acc,none,0.5221774193548387,0.022451211394315496,496,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fb24c7bd9d_2026-09-30T08-20-34.086249.json,1790756205.4627898,1 -v2anneal_120k,include_base_44_polish_social_science,0,lm-eval,vllm,,acc,none,0.75,0.25,4,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fb24c7bd9d_2026-09-30T08-20-34.086249.json,1790756205.4627898,1 -v2anneal_120k,include_base_44_polish_stem,0,lm-eval,vllm,,acc,none,0.375,0.07061658535825402,48,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fb24c7bd9d_2026-09-30T08-20-34.086249.json,1790756205.4627898,1 -v2anneal_120k,include_base_44_portuguese,0,lm-eval,vllm,yes,acc,none,0.6079854809437386,0.020533974972543202,551,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 -v2anneal_120k,include_base_44_portuguese_applied_science,0,lm-eval,vllm,,acc,none,0.5,0.05488212999484517,84,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 -v2anneal_120k,include_base_44_portuguese_arts_humanities,0,lm-eval,vllm,,acc,none,0.6233766233766234,0.03917267027864407,154,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 -v2anneal_120k,include_base_44_portuguese_business_commerce,0,lm-eval,vllm,,acc,none,0.4861111111111111,0.05931618532716555,72,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 -v2anneal_120k,include_base_44_portuguese_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6612903225806451,0.060596141174796975,62,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 -v2anneal_120k,include_base_44_portuguese_social_science,0,lm-eval,vllm,,acc,none,0.7142857142857143,0.03652214232606526,154,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 -v2anneal_120k,include_base_44_portuguese_stem,0,lm-eval,vllm,,acc,none,0.44,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 -v2anneal_120k,include_base_44_serbian,0,lm-eval,vllm,yes,acc,none,0.6709090909090909,0.01992791368582081,550,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5b32a3000_2026-09-30T08-43-21.758999.json,1790757642.9029405,1 -v2anneal_120k,include_base_44_serbian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6293929712460063,0.02734264180492097,313,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5b32a3000_2026-09-30T08-43-21.758999.json,1790757642.9029405,1 -v2anneal_120k,include_base_44_serbian_social_science,0,lm-eval,vllm,,acc,none,0.7540106951871658,0.031578419772456075,187,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5b32a3000_2026-09-30T08-43-21.758999.json,1790757642.9029405,1 -v2anneal_120k,include_base_44_serbian_stem,0,lm-eval,vllm,,acc,none,0.62,0.06934092056863769,50,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5b32a3000_2026-09-30T08-43-21.758999.json,1790757642.9029405,1 -v2anneal_120k,include_base_44_spanish,0,lm-eval,vllm,yes,acc,none,0.6581818181818182,0.02003194252384729,550,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 -v2anneal_120k,include_base_44_spanish_arts_humanities,0,lm-eval,vllm,,acc,none,0.58,0.03127799950463661,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 -v2anneal_120k,include_base_44_spanish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 -v2anneal_120k,include_base_44_spanish_social_science,0,lm-eval,vllm,,acc,none,0.732,0.02806876238252672,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 -v2anneal_120k,include_base_44_spanish_stem,0,lm-eval,vllm,,acc,none,0.76,0.08717797887081347,25,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 -v2anneal_120k,include_base_44_turkish,0,lm-eval,vllm,yes,acc,none,0.5638686131386861,0.020729270503815,548,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 -v2anneal_120k,include_base_44_turkish_arts_humanities,0,lm-eval,vllm,,acc,none,0.536144578313253,0.038823108508905954,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 -v2anneal_120k,include_base_44_turkish_business_commerce,0,lm-eval,vllm,,acc,none,0.7108433734939759,0.035294868015111204,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 -v2anneal_120k,include_base_44_turkish_social_science,0,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 -v2anneal_120k,include_base_44_turkish_stem,0,lm-eval,vllm,,acc,none,0.34,0.0676726816132972,50,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 -v2anneal_120k,include_base_44_ukrainian,0,lm-eval,vllm,yes,acc,none,0.6218181818181818,0.02072253123168508,550,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5949bfffcb_2026-09-30T08-26-13.105199.json,1790756610.9756362,1 -v2anneal_120k,include_base_44_ukrainian_arts_humanities,0,lm-eval,vllm,,acc,none,0.616,0.030821679117375447,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5949bfffcb_2026-09-30T08-26-13.105199.json,1790756610.9756362,1 -v2anneal_120k,include_base_44_ukrainian_social_science,0,lm-eval,vllm,,acc,none,0.636,0.030491555220405475,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5949bfffcb_2026-09-30T08-26-13.105199.json,1790756610.9756362,1 -v2anneal_120k,include_base_44_ukrainian_stem,0,lm-eval,vllm,,acc,none,0.58,0.07050835816716038,50,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5949bfffcb_2026-09-30T08-26-13.105199.json,1790756610.9756362,1 -v2anneal_120k,jeopardy,10,lm-eval,vllm,,exact_match,strict-match,0.5356636750118091,0.010841880009403592,2117,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b91c0afada_2026-09-30T08-49-37.261937.json,1790757989.3484197,1 -v2anneal_120k,lambada_openai,0,lm-eval,vllm,,acc,none,0.7339413933630895,0.006156465073667463,5153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c24cdf9273_2026-09-30T08-43-51.938741.json,1790757643.8164952,1 -v2anneal_120k,lambada_openai,0,lm-eval,vllm,,perplexity,none,3.523157791936209,0.06998351715598007,5153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c24cdf9273_2026-09-30T08-43-51.938741.json,1790757643.8164952,1 -v2anneal_120k,mbpp,3,lm-eval,vllm,,pass_at_1,none,0.622,0.021706550824518184,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/48966cbd64_2026-09-30T08-34-54.493731.json,1790756981.0990462,1 -v2anneal_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.704,0.02892893938837963,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/214d19c231_2026-09-30T08-11-25.206951.json,1790754230.0976589,1 -v2anneal_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,strict-match,0.732,0.02806876238252669,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/214d19c231_2026-09-30T08-11-25.206951.json,1790754230.0976589,1 -v2anneal_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.848,0.022752024491765464,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/23c1d97ca1_2026-09-30T07-40-38.393294.json,1790753866.7507765,1 -v2anneal_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,strict-match,0.788,0.025901884690541166,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/23c1d97ca1_2026-09-30T07-40-38.393294.json,1790753866.7507765,1 -v2anneal_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.828,0.023915513944486218,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/58bda3757f_2026-09-30T07-38-58.499451.json,1790753752.2450347,1 -v2anneal_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,strict-match,0.756,0.02721799546455318,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/58bda3757f_2026-09-30T07-38-58.499451.json,1790753752.2450347,1 -v2anneal_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.684,0.02946265759857868,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/cf19d7ef9a_2026-09-30T08-39-25.252625.json,1790757384.1331484,1 -v2anneal_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,strict-match,0.736,0.02793451895769091,250,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/cf19d7ef9a_2026-09-30T08-39-25.252625.json,1790757384.1331484,1 -v2anneal_120k,mmlu,5,lm-eval,vllm,yes,acc,none,0.7277453354223045,0.0035974184871722203,14042,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_abstract_algebra,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_anatomy,5,lm-eval,vllm,,acc,none,0.6222222222222222,0.041883075375958506,135,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_business_ethics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7509433962264151,0.02661648298050167,265,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_college_biology,5,lm-eval,vllm,,acc,none,0.8611111111111112,0.028919802956134912,144,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_college_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_college_mathematics,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_college_medicine,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.03414014007044037,173,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_computer_security,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7872340425531915,0.02675439134803978,235,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_econometrics,5,lm-eval,vllm,,acc,none,0.5964912280701754,0.04615186962583705,114,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7310344827586207,0.03695183311650232,145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6481481481481481,0.024594975128920938,378,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_formal_logic,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.04285714285714286,126,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_global_facts,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_biology,5,lm-eval,vllm,,acc,none,0.8709677419354839,0.01907088925479277,310,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6798029556650246,0.032826493853041455,203,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8424242424242424,0.02845038880528439,165,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_geography,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.02239078763821682,198,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9637305699481865,0.013492659751295115,193,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7897435897435897,0.020660597485026883,390,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5148148148148148,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8865546218487395,0.020600225750204797,238,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_physics,5,lm-eval,vllm,,acc,none,0.5629139072847682,0.040500357222306375,151,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_psychology,5,lm-eval,vllm,,acc,none,0.9100917431192661,0.012264304540230489,545,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.03167468706828983,216,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8676470588235294,0.02378429752091887,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8818565400843882,0.021011052659878477,237,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_human_aging,5,lm-eval,vllm,,acc,none,0.7623318385650224,0.02856807946471428,223,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_human_sexuality,5,lm-eval,vllm,,acc,none,0.8320610687022901,0.0327854853734314,131,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_humanities,5,lm-eval,vllm,yes,acc,none,0.6814027630180659,0.006513620090495235,4705,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_jurisprudence,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.03602814176392641,108,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7975460122699386,0.031570650789119054,163,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_machine_learning,5,lm-eval,vllm,,acc,none,0.625,0.04595091388086298,112,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_management,5,lm-eval,vllm,,acc,none,0.8349514563106796,0.03675668832233187,103,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_marketing,5,lm-eval,vllm,,acc,none,0.8974358974358975,0.01987565502786746,234,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_medical_genetics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_miscellaneous,5,lm-eval,vllm,,acc,none,0.8378033205619413,0.01318222261672081,783,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_moral_disputes,5,lm-eval,vllm,,acc,none,0.7947976878612717,0.021742519835276364,346,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5418994413407822,0.016663683295020503,895,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_nutrition,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.024848018263875137,306,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_other,5,lm-eval,vllm,yes,acc,none,0.7444480205986482,0.0075766412475204575,3107,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_philosophy,5,lm-eval,vllm,,acc,none,0.752411575562701,0.024513879973621984,311,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_prehistory,5,lm-eval,vllm,,acc,none,0.8395061728395061,0.02042395535477805,324,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_professional_accounting,5,lm-eval,vllm,,acc,none,0.5390070921985816,0.029736592526424455,282,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_professional_law,5,lm-eval,vllm,,acc,none,0.5664928292046936,0.012656810383983882,1534,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_professional_medicine,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.026799562024887664,272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_professional_psychology,5,lm-eval,vllm,,acc,none,0.75,0.01751781884501444,612,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_public_relations,5,lm-eval,vllm,,acc,none,0.7181818181818181,0.043091187099464606,110,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8277543061423465,0.00665014813921035,3077,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_sociology,5,lm-eval,vllm,,acc,none,0.8706467661691543,0.02372983088101855,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_stem,5,lm-eval,vllm,yes,acc,none,0.6828417380272757,0.008021755838114007,3153,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_virology,5,lm-eval,vllm,,acc,none,0.5481927710843374,0.0387437155658795,166,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,mmlu_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 -v2anneal_120k,multiblimp_bul,0,lm-eval,vllm,,acc,none,0.984947111472742,0.0024564832092906753,2458,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fd93079d3e_2026-09-30T08-32-56.851583.json,1790757012.2006617,1 -v2anneal_120k,multiblimp_bul,0,lm-eval,vllm,,acc_norm,none,0.9772172497965825,0.0030102048992459093,2458,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fd93079d3e_2026-09-30T08-32-56.851583.json,1790757012.2006617,1 -v2anneal_120k,multiblimp_cat,0,lm-eval,vllm,,acc,none,0.9772329246935202,0.0031217614380178514,2284,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/29d71a90c9_2026-09-30T08-47-42.729319.json,1790757887.8651025,1 -v2anneal_120k,multiblimp_cat,0,lm-eval,vllm,,acc_norm,none,0.9776707530647986,0.0030922912692911255,2284,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/29d71a90c9_2026-09-30T08-47-42.729319.json,1790757887.8651025,1 -v2anneal_120k,multiblimp_ces,0,lm-eval,vllm,,acc,none,0.9518327067669173,0.0032825144805596292,4256,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2437361283_2026-09-30T08-52-49.665259.json,1790758109.0033753,1 -v2anneal_120k,multiblimp_ces,0,lm-eval,vllm,,acc_norm,none,0.9541823308270677,0.0032054012276831923,4256,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2437361283_2026-09-30T08-52-49.665259.json,1790758109.0033753,1 -v2anneal_120k,multiblimp_dan,0,lm-eval,vllm,,acc,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95ba6406d1_2026-09-30T08-35-57.676389.json,1790757134.6447525,1 -v2anneal_120k,multiblimp_dan,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95ba6406d1_2026-09-30T08-35-57.676389.json,1790757134.6447525,1 -v2anneal_120k,multiblimp_deu,0,lm-eval,vllm,,acc,none,0.9873803307223673,0.0023290870729458513,2298,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e1650c6000_2026-09-30T08-31-30.409241.json,1790756929.1146824,1 -v2anneal_120k,multiblimp_deu,0,lm-eval,vllm,,acc_norm,none,0.9852045256744996,0.002519110092348522,2298,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e1650c6000_2026-09-30T08-31-30.409241.json,1790756929.1146824,1 -v2anneal_120k,multiblimp_ell,0,lm-eval,vllm,,acc,none,0.9945255474452555,0.0022298274651133573,1096,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e59f0e973b_2026-09-30T07-40-29.956193.json,1790753865.2941065,1 -v2anneal_120k,multiblimp_ell,0,lm-eval,vllm,,acc_norm,none,0.9981751824817519,0.0012897515102687142,1096,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e59f0e973b_2026-09-30T07-40-29.956193.json,1790753865.2941065,1 -v2anneal_120k,multiblimp_eng,0,lm-eval,vllm,,acc,none,0.9935064935064936,0.002896421914185563,770,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9e55c73926_2026-09-30T08-43-09.228610.json,1790757644.6146133,1 -v2anneal_120k,multiblimp_eng,0,lm-eval,vllm,,acc_norm,none,0.9883116883116884,0.0038757850932000515,770,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9e55c73926_2026-09-30T08-43-09.228610.json,1790757644.6146133,1 -v2anneal_120k,multiblimp_est,0,lm-eval,vllm,,acc,none,0.9044660194174757,0.0057938973043891746,2575,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/83546e4990_2026-09-30T07-34-35.973067.json,1790753499.5758636,1 -v2anneal_120k,multiblimp_est,0,lm-eval,vllm,,acc_norm,none,0.9009708737864077,0.005887522474827137,2575,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/83546e4990_2026-09-30T07-34-35.973067.json,1790753499.5758636,1 -v2anneal_120k,multiblimp_eus,0,lm-eval,vllm,,acc,none,0.9487179487179487,0.0133741688167181,273,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/924c69e5f9_2026-09-30T08-38-46.315998.json,1790757382.793441,1 -v2anneal_120k,multiblimp_eus,0,lm-eval,vllm,,acc_norm,none,0.6227106227106227,0.029389755560222004,273,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/924c69e5f9_2026-09-30T08-38-46.315998.json,1790757382.793441,1 -v2anneal_120k,multiblimp_fin,0,lm-eval,vllm,,acc,none,0.9389105058365759,0.004725125105853984,2570,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/baf1cdb786_2026-09-30T08-11-16.663762.json,1790754230.6025035,1 -v2anneal_120k,multiblimp_fin,0,lm-eval,vllm,,acc_norm,none,0.932295719844358,0.004956816657465678,2570,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/baf1cdb786_2026-09-30T08-11-16.663762.json,1790754230.6025035,1 -v2anneal_120k,multiblimp_fra,0,lm-eval,vllm,,acc,none,0.9913657770800628,0.0018332180191281344,2548,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7780230490_2026-09-30T07-44-50.054559.json,1790754121.1507268,1 -v2anneal_120k,multiblimp_fra,0,lm-eval,vllm,,acc_norm,none,0.9862637362637363,0.0023063030340050696,2548,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7780230490_2026-09-30T07-44-50.054559.json,1790754121.1507268,1 -v2anneal_120k,multiblimp_gle,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.06734350297014738,28,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9ee5047ae8_2026-09-30T07-34-20.477366.json,1790753513.6247275,1 -v2anneal_120k,multiblimp_gle,0,lm-eval,vllm,,acc_norm,none,0.75,0.08333333333333333,28,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9ee5047ae8_2026-09-30T07-34-20.477366.json,1790753513.6247275,1 -v2anneal_120k,multiblimp_glg,0,lm-eval,vllm,,acc,none,0.9681274900398407,0.006405683674396879,753,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/705c91b2a9_2026-09-30T08-21-01.990554.json,1790756304.2746775,1 -v2anneal_120k,multiblimp_glg,0,lm-eval,vllm,,acc_norm,none,0.952191235059761,0.007780489692849838,753,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/705c91b2a9_2026-09-30T08-21-01.990554.json,1790756304.2746775,1 -v2anneal_120k,multiblimp_hbs,0,lm-eval,vllm,,acc,none,0.9768715763846622,0.0026225517472673564,3286,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e5256329a7_2026-09-30T08-43-31.324693.json,1790757623.6114643,1 -v2anneal_120k,multiblimp_hbs,0,lm-eval,vllm,,acc_norm,none,0.9765672550213025,0.00263933778428641,3286,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e5256329a7_2026-09-30T08-43-31.324693.json,1790757623.6114643,1 -v2anneal_120k,multiblimp_hun,0,lm-eval,vllm,,acc,none,0.9810650887573964,0.004691474113624961,845,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a83b7d0e38_2026-09-30T08-20-25.207801.json,1790756205.1350284,1 -v2anneal_120k,multiblimp_hun,0,lm-eval,vllm,,acc_norm,none,0.9798816568047337,0.004832943264222541,845,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a83b7d0e38_2026-09-30T08-20-25.207801.json,1790756205.1350284,1 -v2anneal_120k,multiblimp_isl,0,lm-eval,vllm,,acc,none,0.9696536951088897,0.0032417701662697277,2801,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0ea4a5db28_2026-09-30T08-14-24.739510.json,1790755830.2465158,1 -v2anneal_120k,multiblimp_isl,0,lm-eval,vllm,,acc_norm,none,0.9625133880756872,0.0035897356573365,2801,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0ea4a5db28_2026-09-30T08-14-24.739510.json,1790755830.2465158,1 -v2anneal_120k,multiblimp_ita,0,lm-eval,vllm,,acc,none,0.9619873291097032,0.0034924729766106738,2999,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0dd099535_2026-09-30T08-23-03.181288.json,1790756405.6435413,1 -v2anneal_120k,multiblimp_ita,0,lm-eval,vllm,,acc_norm,none,0.9539846615538513,0.0038265394236287995,2999,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0dd099535_2026-09-30T08-23-03.181288.json,1790756405.6435413,1 -v2anneal_120k,multiblimp_kat,0,lm-eval,vllm,,acc,none,0.9558823529411765,0.014413198705704818,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/81cc5995ca_2026-09-30T08-31-41.707415.json,1790756930.2532284,1 -v2anneal_120k,multiblimp_kat,0,lm-eval,vllm,,acc_norm,none,0.9117647058823529,0.01990739979131697,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/81cc5995ca_2026-09-30T08-31-41.707415.json,1790756930.2532284,1 -v2anneal_120k,multiblimp_lav,0,lm-eval,vllm,,acc,none,0.9604221635883905,0.0035413116097079414,3032,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c29251978_2026-09-30T08-33-19.491316.json,1790757005.622636,1 -v2anneal_120k,multiblimp_lav,0,lm-eval,vllm,,acc_norm,none,0.9564643799472295,0.0037064982500016564,3032,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c29251978_2026-09-30T08-33-19.491316.json,1790757005.622636,1 -v2anneal_120k,multiblimp_lit,0,lm-eval,vllm,,acc,none,0.9813559322033898,0.003939369428601548,1180,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/180842076e_2026-09-30T08-11-03.581154.json,1790754229.9082053,1 -v2anneal_120k,multiblimp_lit,0,lm-eval,vllm,,acc_norm,none,0.9805084745762712,0.004026166098461977,1180,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/180842076e_2026-09-30T08-11-03.581154.json,1790754229.9082053,1 -v2anneal_120k,multiblimp_mkd,0,lm-eval,vllm,,acc,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/38e1622f9b_2026-09-30T08-31-18.349890.json,1790756931.1874237,1 -v2anneal_120k,multiblimp_mkd,0,lm-eval,vllm,,acc_norm,none,0.9230769230769231,0.043227037457616635,39,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/38e1622f9b_2026-09-30T08-31-18.349890.json,1790756931.1874237,1 -v2anneal_120k,multiblimp_nld,0,lm-eval,vllm,,acc,none,0.9515229515229515,0.004449382666732822,2331,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4976faba87_2026-09-30T08-39-06.135503.json,1790757372.8123157,1 -v2anneal_120k,multiblimp_nld,0,lm-eval,vllm,,acc_norm,none,0.924924924924925,0.00545912663303515,2331,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4976faba87_2026-09-30T08-39-06.135503.json,1790757372.8123157,1 -v2anneal_120k,multiblimp_pol,0,lm-eval,vllm,,acc,none,0.9584352078239609,0.003489827126709908,3272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3eb43b31ad_2026-09-30T08-31-41.030189.json,1790756931.2251399,1 -v2anneal_120k,multiblimp_pol,0,lm-eval,vllm,,acc_norm,none,0.9391809290953546,0.004178825645109273,3272,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3eb43b31ad_2026-09-30T08-31-41.030189.json,1790756931.2251399,1 -v2anneal_120k,multiblimp_por,0,lm-eval,vllm,,acc,none,0.9724409448818898,0.0029657022925976134,3048,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1502915446_2026-09-30T08-20-42.648171.json,1790756204.654618,1 -v2anneal_120k,multiblimp_por,0,lm-eval,vllm,,acc_norm,none,0.9698162729658792,0.003099523537944906,3048,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1502915446_2026-09-30T08-20-42.648171.json,1790756204.654618,1 -v2anneal_120k,multiblimp_ron,0,lm-eval,vllm,,acc,none,0.9630350194552529,0.004162079465649507,2056,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/56523d5db9_2026-09-30T08-37-23.814875.json,1790757280.8378541,1 -v2anneal_120k,multiblimp_ron,0,lm-eval,vllm,,acc_norm,none,0.958171206225681,0.004416246591731525,2056,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/56523d5db9_2026-09-30T08-37-23.814875.json,1790757280.8378541,1 -v2anneal_120k,multiblimp_slk,0,lm-eval,vllm,,acc,none,0.9437876960193003,0.003578021742558625,4145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c8ceea0aa4_2026-09-30T08-14-25.156563.json,1790755617.9412036,1 -v2anneal_120k,multiblimp_slk,0,lm-eval,vllm,,acc_norm,none,0.944270205066345,0.0035635429073718815,4145,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c8ceea0aa4_2026-09-30T08-14-25.156563.json,1790755617.9412036,1 -v2anneal_120k,multiblimp_slv,0,lm-eval,vllm,,acc,none,0.9326343966094134,0.0037440262956893364,4483,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fe42d4d144_2026-09-30T07-34-53.986753.json,1790753469.5036514,1 -v2anneal_120k,multiblimp_slv,0,lm-eval,vllm,,acc_norm,none,0.9223734106625028,0.003996894766503557,4483,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fe42d4d144_2026-09-30T07-34-53.986753.json,1790753469.5036514,1 -v2anneal_120k,multiblimp_spa,0,lm-eval,vllm,,acc,none,0.9822904368358913,0.0026170198938226304,2541,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8b08e09b56_2026-09-30T07-38-45.004933.json,1790753750.671699,1 -v2anneal_120k,multiblimp_spa,0,lm-eval,vllm,,acc_norm,none,0.983077528532074,0.0025592276630338104,2541,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8b08e09b56_2026-09-30T07-38-45.004933.json,1790753750.671699,1 -v2anneal_120k,multiblimp_sqi,0,lm-eval,vllm,,acc,none,0.9465020576131687,0.01446510656878504,243,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/762fbe30a8_2026-09-30T07-38-12.286719.json,1790753749.6544251,1 -v2anneal_120k,multiblimp_sqi,0,lm-eval,vllm,,acc_norm,none,0.9012345679012346,0.019178459585449004,243,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/762fbe30a8_2026-09-30T07-38-12.286719.json,1790753749.6544251,1 -v2anneal_120k,multiblimp_swe,0,lm-eval,vllm,,acc,none,0.9950248756218906,0.004975124378109453,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/be61369270_2026-09-30T08-26-46.052029.json,1790756651.2086518,1 -v2anneal_120k,multiblimp_swe,0,lm-eval,vllm,,acc_norm,none,0.9900497512437811,0.007018276606798947,201,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/be61369270_2026-09-30T08-26-46.052029.json,1790756651.2086518,1 -v2anneal_120k,multiblimp_tur,0,lm-eval,vllm,,acc,none,0.9064293915040184,0.0069797092363050525,1742,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ea946abb1b_2026-09-30T08-26-10.397916.json,1790756611.6366866,1 -v2anneal_120k,multiblimp_tur,0,lm-eval,vllm,,acc_norm,none,0.8461538461538461,0.008647062590129767,1742,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ea946abb1b_2026-09-30T08-26-10.397916.json,1790756611.6366866,1 -v2anneal_120k,multiblimp_ukr,0,lm-eval,vllm,,acc,none,0.9795918367346939,0.0026996759326348425,2744,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd398eb3a2_2026-09-30T08-45-26.360584.json,1790757750.4302871,1 -v2anneal_120k,multiblimp_ukr,0,lm-eval,vllm,,acc_norm,none,0.9719387755102041,0.0031532605656132426,2744,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd398eb3a2_2026-09-30T08-45-26.360584.json,1790757750.4302871,1 -v2anneal_120k,openbookqa,0,lm-eval,vllm,,acc,none,0.348,0.021323728632807425,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cdb44fab1_2026-09-30T08-37-25.800861.json,1790757281.0389993,1 -v2anneal_120k,openbookqa,0,lm-eval,vllm,,acc_norm,none,0.446,0.022252153078595936,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cdb44fab1_2026-09-30T08-37-25.800861.json,1790757281.0389993,1 -v2anneal_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,bleu,none,15.003650618866999,0.2640478125195402,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/254d53288f_2026-09-30T08-53-07.176457.json,1790758110.3719418,1 -v2anneal_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,chrf,none,33.51244895183558,0.30424075494002356,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/254d53288f_2026-09-30T08-53-07.176457.json,1790758110.3719418,1 -v2anneal_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,bleu,none,24.287465757521666,0.2767299568481002,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/243dd202fa_2026-09-30T08-33-29.472801.json,1790756930.1446486,1 -v2anneal_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,chrf,none,42.93742966081114,0.2513793268225009,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/243dd202fa_2026-09-30T08-33-29.472801.json,1790756930.1446486,1 -v2anneal_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,bleu,none,29.978766998472672,0.33278654183215584,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0f14ca7da4_2026-09-30T08-45-26.712738.json,1790757646.391393,1 -v2anneal_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,chrf,none,49.13262126141007,0.27072821166642186,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0f14ca7da4_2026-09-30T08-45-26.712738.json,1790757646.391393,1 -v2anneal_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,bleu,none,26.533052554215498,0.31660376659960104,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/52f4aeb8b0_2026-09-30T16-53-06.329376.json,1790786894.1423683,1 -v2anneal_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,chrf,none,46.47287400648327,0.28401287229377115,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/52f4aeb8b0_2026-09-30T16-53-06.329376.json,1790786894.1423683,1 -v2anneal_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,bleu,none,28.53342457274273,0.35851197786269856,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7824c3562d_2026-09-30T08-40-52.607785.json,1790757372.7801106,1 -v2anneal_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,chrf,none,46.94123205165745,0.3223752216868438,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7824c3562d_2026-09-30T08-40-52.607785.json,1790757372.7801106,1 -v2anneal_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,bleu,none,12.06991503307192,0.2566605620445614,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1560b8ce00_2026-09-30T08-16-52.301574.json,1790755924.9914212,1 -v2anneal_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,chrf,none,36.26491350440361,0.3230513608892678,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1560b8ce00_2026-09-30T08-16-52.301574.json,1790755924.9914212,1 -v2anneal_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,bleu,none,17.73760258494243,0.2890172152738235,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/de5685eb7e_2026-09-30T08-55-16.893905.json,1790758233.8252575,1 -v2anneal_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,chrf,none,40.40293124431965,0.2426036934530269,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/de5685eb7e_2026-09-30T08-55-16.893905.json,1790758233.8252575,1 -v2anneal_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,bleu,none,29.46689780485439,0.3178939458562562,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f58a23c313_2026-09-30T08-28-14.275106.json,1790756609.707454,1 -v2anneal_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,chrf,none,51.45074381089818,0.25198153861091005,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f58a23c313_2026-09-30T08-28-14.275106.json,1790756609.707454,1 -v2anneal_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,bleu,none,22.58397892805329,0.33834839392266836,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/164798c773_2026-09-30T08-25-11.985623.json,1790756403.3089743,1 -v2anneal_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,chrf,none,47.30599141902181,0.3113692661003813,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/164798c773_2026-09-30T08-25-11.985623.json,1790756403.3089743,1 -v2anneal_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,bleu,none,21.889178171188618,0.33952033480092003,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b15951784b_2026-09-30T07-42-59.228838.json,1790753865.981722,1 -v2anneal_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,chrf,none,43.44546833425687,0.3160119427452474,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b15951784b_2026-09-30T07-42-59.228838.json,1790753865.981722,1 -v2anneal_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,bleu,none,28.385013188787394,0.3706904651286205,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7f7b8db687_2026-09-30T08-45-09.388305.json,1790757622.0427928,1 -v2anneal_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,chrf,none,50.03014751103492,0.33848535604583513,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7f7b8db687_2026-09-30T08-45-09.388305.json,1790757622.0427928,1 -v2anneal_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,bleu,none,21.705449936407522,0.3476460560068148,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6289986c3_2026-09-30T08-28-29.250542.json,1790756611.5832756,1 -v2anneal_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,chrf,none,45.35800754478377,0.2597731358802138,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6289986c3_2026-09-30T08-28-29.250542.json,1790756611.5832756,1 -v2anneal_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,bleu,none,16.77894598071746,0.3369373356404649,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e026493e54_2026-09-30T08-40-53.271183.json,1790757372.8209233,1 -v2anneal_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,chrf,none,45.845114301587806,0.2476938621269921,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e026493e54_2026-09-30T08-40-53.271183.json,1790757372.8209233,1 -v2anneal_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,bleu,none,15.64501725950506,0.2347428809936428,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/15f15bb785_2026-09-30T08-51-30.861043.json,1790757990.28161,1 -v2anneal_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,chrf,none,41.8703322995393,0.27165318914016173,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/15f15bb785_2026-09-30T08-51-30.861043.json,1790757990.28161,1 -v2anneal_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,bleu,none,25.59032748310354,0.31229139405300194,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0f4f4a4f11_2026-09-30T08-34-55.105435.json,1790757010.440211,1 -v2anneal_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,chrf,none,53.01937756038305,0.2561923271366798,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0f4f4a4f11_2026-09-30T08-34-55.105435.json,1790757010.440211,1 -v2anneal_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,bleu,none,17.061013299325463,0.27042527602165894,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f21f3f4129_2026-09-30T07-36-41.935735.json,1790753513.6043768,1 -v2anneal_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,chrf,none,40.29816848135213,0.2411277445556396,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f21f3f4129_2026-09-30T07-36-41.935735.json,1790753513.6043768,1 -v2anneal_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,bleu,none,27.867270653374906,0.36381265112931677,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d3cb1b10d0_2026-09-30T08-23-11.799042.json,1790756302.5977905,1 -v2anneal_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,chrf,none,50.22688626715382,0.2841581782125067,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d3cb1b10d0_2026-09-30T08-23-11.799042.json,1790756302.5977905,1 -v2anneal_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,bleu,none,18.525758021609157,0.289716197800278,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f57f2cf6ad_2026-09-30T07-36-50.295715.json,1790753513.7625396,1 -v2anneal_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,chrf,none,43.03170468479124,0.2339174077703083,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f57f2cf6ad_2026-09-30T07-36-50.295715.json,1790753513.7625396,1 -v2anneal_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,bleu,none,21.290054084799436,0.3290764099697444,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0524013ad0_2026-09-30T08-51-25.359351.json,1790757989.5639303,1 -v2anneal_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,chrf,none,44.92578462272227,0.24275415950233947,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0524013ad0_2026-09-30T08-51-25.359351.json,1790757989.5639303,1 -v2anneal_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,bleu,none,20.145734697908825,0.280501878341418,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac7843847e_2026-09-30T08-28-24.312806.json,1790756611.0908015,1 -v2anneal_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,chrf,none,46.2020415806725,0.2296496794525854,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac7843847e_2026-09-30T08-28-24.312806.json,1790756611.0908015,1 -v2anneal_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,bleu,none,30.855543527173815,0.3083742476762461,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4096fbae59_2026-09-30T08-44-34.229123.json,1790757572.4025536,1 -v2anneal_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,chrf,none,54.28100232910595,0.2884988778566187,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4096fbae59_2026-09-30T08-44-34.229123.json,1790757572.4025536,1 -v2anneal_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,bleu,none,20.995299381934533,0.3524491906204629,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b650c29367_2026-09-30T08-45-50.758022.json,1790757646.438095,1 -v2anneal_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,chrf,none,45.893538079574135,0.28110560471292106,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b650c29367_2026-09-30T08-45-50.758022.json,1790757646.438095,1 -v2anneal_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,bleu,none,24.58250681034448,0.29862282018317043,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/01e90882e0_2026-09-30T08-39-40.808204.json,1790757279.7737458,1 -v2anneal_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,chrf,none,50.71973943924048,0.2603471087477354,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/01e90882e0_2026-09-30T08-39-40.808204.json,1790757279.7737458,1 -v2anneal_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,bleu,none,25.76001460058189,0.3925544122927604,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c38fdc963e_2026-09-30T08-24-58.577260.json,1790756401.6354928,1 -v2anneal_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,chrf,none,49.840842672049426,0.30549879066607116,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c38fdc963e_2026-09-30T08-24-58.577260.json,1790756401.6354928,1 -v2anneal_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,bleu,none,24.780025615180204,0.3565446556945002,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b400e8993e_2026-09-30T08-15-21.595163.json,1790755617.97272,1 -v2anneal_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,chrf,none,47.07280552178489,0.2510125642597503,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b400e8993e_2026-09-30T08-15-21.595163.json,1790755617.97272,1 -v2anneal_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,bleu,none,15.919063244134337,0.2692026366641734,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4625dddc43_2026-09-30T08-45-28.142244.json,1790757643.9533594,1 -v2anneal_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,chrf,none,42.178713341078435,0.257317283215899,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4625dddc43_2026-09-30T08-45-28.142244.json,1790757643.9533594,1 -v2anneal_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,bleu,none,19.783467403594074,0.3495074887116293,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b932b9c997_2026-09-30T16-53-11.805213.json,1790786902.5669606,1 -v2anneal_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,chrf,none,39.914268318330095,0.4614420792498697,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b932b9c997_2026-09-30T16-53-11.805213.json,1790786902.5669606,1 -v2anneal_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,bleu,none,33.03433486457814,0.3456247721252961,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/184aa56f36_2026-09-30T08-15-26.763597.json,1790755617.9424443,1 -v2anneal_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,chrf,none,53.24908306073861,0.31492520088834447,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/184aa56f36_2026-09-30T08-15-26.763597.json,1790755617.9424443,1 -v2anneal_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,bleu,none,20.68107561104388,0.35915687539291524,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1b5e77e39b_2026-09-30T08-39-40.789987.json,1790757281.2179785,1 -v2anneal_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,chrf,none,48.64754938596812,0.29605691206317286,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1b5e77e39b_2026-09-30T08-39-40.789987.json,1790757281.2179785,1 -v2anneal_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,bleu,none,16.705421272378242,0.2633416845167624,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/037cf1f3e3_2026-09-30T07-36-26.059552.json,1790753469.2214413,1 -v2anneal_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,chrf,none,38.26208638576516,0.25301480909423996,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/037cf1f3e3_2026-09-30T07-36-26.059552.json,1790753469.2214413,1 -v2anneal_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,bleu,none,29.421452431470037,0.32458241325941467,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/339108969b_2026-09-30T08-20-20.508829.json,1790756125.8833287,1 -v2anneal_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,chrf,none,47.781699805853194,0.31836642040344765,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/339108969b_2026-09-30T08-20-20.508829.json,1790756125.8833287,1 -v2anneal_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,bleu,none,28.061321049800746,0.3417258778656989,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2cbb54ed6e_2026-09-30T08-21-29.233441.json,1790756204.8603153,1 -v2anneal_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,chrf,none,46.802765071196426,0.2728225863730105,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2cbb54ed6e_2026-09-30T08-21-29.233441.json,1790756204.8603153,1 -v2anneal_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,bleu,none,23.14526492362293,0.31722385658429425,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/aa6cb573d5_2026-09-30T08-50-57.999335.json,1790757959.9055662,1 -v2anneal_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,chrf,none,42.890376018543556,0.2603689928410946,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/aa6cb573d5_2026-09-30T08-50-57.999335.json,1790757959.9055662,1 -v2anneal_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,bleu,none,16.997531847170016,0.2555695170525282,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c1836b0768_2026-09-30T08-33-24.141971.json,1790756929.4831698,1 -v2anneal_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,chrf,none,35.01414914469773,0.28821738525247687,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c1836b0768_2026-09-30T08-33-24.141971.json,1790756929.4831698,1 -v2anneal_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,bleu,none,29.856998549113236,0.3913527154196685,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0d927ed6a6_2026-09-30T08-06-50.709866.json,1790754113.534177,1 -v2anneal_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,chrf,none,49.34814681616648,0.3248485770785364,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0d927ed6a6_2026-09-30T08-06-50.709866.json,1790754113.534177,1 -v2anneal_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,bleu,none,22.50774023429512,0.2868998352674406,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/360a5d2ae7_2026-09-30T16-53-06.317467.json,1790786894.1421666,1 -v2anneal_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,chrf,none,41.06392598464278,0.23666832130981091,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/360a5d2ae7_2026-09-30T16-53-06.317467.json,1790786894.1421666,1 -v2anneal_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,bleu,none,29.64830520634905,0.3253963591089322,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26d94f2743_2026-09-30T07-40-35.308510.json,1790753750.9416914,1 -v2anneal_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,chrf,none,47.28039758188727,0.2940858179971653,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26d94f2743_2026-09-30T07-40-35.308510.json,1790753750.9416914,1 -v2anneal_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,bleu,none,26.247786498125055,0.3551103835349797,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3050f2a1e_2026-09-30T08-15-21.379186.json,1790755617.8509512,1 -v2anneal_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,chrf,none,44.16699374920105,0.2732754115438893,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3050f2a1e_2026-09-30T08-15-21.379186.json,1790755617.8509512,1 -v2anneal_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,bleu,none,27.186913764167596,0.32908472060838384,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d0ef94c0c9_2026-09-30T08-35-09.533611.json,1790757011.3854713,1 -v2anneal_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,chrf,none,45.67520805121994,0.2783786339310545,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d0ef94c0c9_2026-09-30T08-35-09.533611.json,1790757011.3854713,1 -v2anneal_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,bleu,none,22.74723511435326,0.27378377269472687,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/978368894d_2026-09-30T08-21-34.587276.json,1790756204.313334,1 -v2anneal_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,chrf,none,41.82982284299739,0.2359548048961488,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/978368894d_2026-09-30T08-21-34.587276.json,1790756204.313334,1 -v2anneal_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,bleu,none,31.384082143878654,0.2995990117103854,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/079b6bfc66_2026-09-30T08-40-55.381661.json,1790757372.8387737,1 -v2anneal_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,chrf,none,49.99679336635449,0.2523122123643974,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/079b6bfc66_2026-09-30T08-40-55.381661.json,1790757372.8387737,1 -v2anneal_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,bleu,none,26.257974285917662,0.32341369808266546,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/84e4b3f22f_2026-09-30T08-39-59.090663.json,1790757281.347818,1 -v2anneal_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,chrf,none,45.21653497053772,0.2753078119621563,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/84e4b3f22f_2026-09-30T08-39-59.090663.json,1790757281.347818,1 -v2anneal_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,bleu,none,29.954423622085674,0.3619846349487159,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/37fc80bb53_2026-09-30T07-42-25.354874.json,1790753864.9287243,1 -v2anneal_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,chrf,none,46.666919289096846,0.3537706498926314,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/37fc80bb53_2026-09-30T07-42-25.354874.json,1790753864.9287243,1 -v2anneal_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,bleu,none,31.215816623901514,0.3861614057450715,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1da297fd33_2026-09-30T07-36-21.050886.json,1790753469.3663568,1 -v2anneal_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,chrf,none,48.58454514033967,0.3235490481686245,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1da297fd33_2026-09-30T07-36-21.050886.json,1790753469.3663568,1 -v2anneal_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,bleu,none,31.52243061668225,0.3321225075204656,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/332f2059e8_2026-09-30T08-55-22.512505.json,1790758230.1469233,1 -v2anneal_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,chrf,none,49.26981564082949,0.2710033922723419,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/332f2059e8_2026-09-30T08-55-22.512505.json,1790758230.1469233,1 -v2anneal_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,bleu,none,20.764014890306164,0.2825665005463853,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0e0f89c84_2026-09-30T08-28-16.858677.json,1790756611.2532654,1 -v2anneal_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,chrf,none,40.37642265053128,0.2558400529702662,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0e0f89c84_2026-09-30T08-28-16.858677.json,1790756611.2532654,1 -v2anneal_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,bleu,none,31.186399460110632,0.33669396333167223,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8a6cd1adc9_2026-09-30T08-13-16.929679.json,1790754225.6585321,1 -v2anneal_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,chrf,none,51.369319677751626,0.2565774608301896,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8a6cd1adc9_2026-09-30T08-13-16.929679.json,1790754225.6585321,1 -v2anneal_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,bleu,none,36.51785372638628,0.33933011267367824,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/54fc6b52fc_2026-09-30T08-24-48.520726.json,1790756405.5726144,1 -v2anneal_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,chrf,none,53.31416207375435,0.29360439008066735,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/54fc6b52fc_2026-09-30T08-24-48.520726.json,1790756405.5726144,1 -v2anneal_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,bleu,none,27.934500026684724,0.2803910451172384,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4181529a39_2026-09-30T07-40-41.524062.json,1790753750.4776633,1 -v2anneal_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,chrf,none,47.33245449153864,0.2550935392987942,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4181529a39_2026-09-30T07-40-41.524062.json,1790753750.4776633,1 -v2anneal_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,bleu,none,22.962690926896595,0.32151042833384175,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d137c03714_2026-09-30T08-50-38.714068.json,1790757958.284796,1 -v2anneal_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,chrf,none,41.54576871302295,0.28100575791765875,6005,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d137c03714_2026-09-30T08-50-38.714068.json,1790757958.284796,1 -v2anneal_120k,piqa,0,lm-eval,vllm,,acc,none,0.8122959738846572,0.009110440292132566,1838,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-21-10.381633.json,1790810334.1842988,1 -v2anneal_120k,piqa,0,lm-eval,vllm,,acc_norm,none,0.8193688792165397,0.00897597103733801,1838,/e/scratch/e-sta-openeurollm/vanosch1/fewshot_test/runs/v2anneal_120k/2126606/results/r_2026-09-30T23-21-10.381633.json,1790810334.1842988,1 -v2anneal_120k,piqa,10,lm-eval,vllm,,acc,none,0.8280739934711643,0.008803407033583992,1838,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c8f538ebc7_2026-09-30T07-35-00.490064.json,1790753510.465127,1 -v2anneal_120k,piqa,10,lm-eval,vllm,,acc_norm,none,0.8373231773667029,0.008611024380872861,1838,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c8f538ebc7_2026-09-30T07-35-00.490064.json,1790753510.465127,1 -v2anneal_120k,polymath_de_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f6f3e1f294_2026-09-30T08-27-18.486487.json,1790756652.4967537,1 -v2anneal_120k,polymath_de_low,0,lm-eval,vllm,,exact_match,none,0.448,0.04465783896075986,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417254040e_2026-09-30T08-33-17.340591.json,1790757011.5856013,1 -v2anneal_120k,polymath_de_medium,0,lm-eval,vllm,,exact_match,none,0.048,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f7aada5b92_2026-09-30T07-34-52.021714.json,1790753498.2367218,1 -v2anneal_120k,polymath_de_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b0ba05a35e_2026-09-30T08-49-11.083958.json,1790757959.9288003,1 -v2anneal_120k,polymath_en_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9c34e0866f_2026-09-30T08-27-12.939236.json,1790756643.1978827,1 -v2anneal_120k,polymath_en_low,0,lm-eval,vllm,,exact_match,none,0.704,0.04099409870984186,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/89f59bfec9_2026-09-30T08-14-36.552167.json,1790755619.2151055,1 -v2anneal_120k,polymath_en_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/20abc30d97_2026-09-30T08-49-46.286521.json,1790757994.957994,1 -v2anneal_120k,polymath_en_top,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/56a52b4610_2026-09-30T08-27-02.418563.json,1790756644.905558,1 -v2anneal_120k,polymath_es_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d5df9ab151_2026-09-30T07-42-52.121431.json,1790753985.4851134,1 -v2anneal_120k,polymath_es_low,0,lm-eval,vllm,,exact_match,none,0.592,0.044134691204787364,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/282e5c3a18_2026-09-30T07-45-00.310238.json,1790754115.3406901,1 -v2anneal_120k,polymath_es_medium,0,lm-eval,vllm,,exact_match,none,0.048,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a659b650e4_2026-09-30T07-39-01.057946.json,1790753750.7890701,1 -v2anneal_120k,polymath_es_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8642eb41b6_2026-09-30T08-43-31.800525.json,1790757621.8780978,1 -v2anneal_120k,polymath_fr_high,0,lm-eval,vllm,,exact_match,none,0.04,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69bf33debd_2026-09-30T07-41-11.819919.json,1790753868.6236207,1 -v2anneal_120k,polymath_fr_low,0,lm-eval,vllm,,exact_match,none,0.552,0.04465783896075985,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/71a6972035_2026-09-30T07-40-50.964486.json,1790753868.0946627,1 -v2anneal_120k,polymath_fr_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/aa41cb4b61_2026-09-30T08-33-17.473013.json,1790757015.1166463,1 -v2anneal_120k,polymath_fr_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/58285c6fb5_2026-09-30T07-45-01.826734.json,1790754117.6309142,1 -v2anneal_120k,polymath_it_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6c154cc864_2026-09-30T07-34-33.474585.json,1790753468.5649738,1 -v2anneal_120k,polymath_it_low,0,lm-eval,vllm,,exact_match,none,0.56,0.04457686366483793,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9c3378aa3f_2026-09-30T08-20-55.457299.json,1790756204.2982337,1 -v2anneal_120k,polymath_it_medium,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5d04e90559_2026-09-30T07-45-14.113052.json,1790754117.8321943,1 -v2anneal_120k,polymath_it_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1df49e802d_2026-09-30T08-20-55.784192.json,1790756203.6029656,1 -v2anneal_120k,polymath_pt_high,0,lm-eval,vllm,,exact_match,none,0.04,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/299ae1443a_2026-09-30T08-27-10.164757.json,1790756650.7965853,1 -v2anneal_120k,polymath_pt_low,0,lm-eval,vllm,,exact_match,none,0.488,0.044888392062263534,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fdf24c8b0_2026-09-30T08-45-27.317003.json,1790757745.5037408,1 -v2anneal_120k,polymath_pt_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/27685c5c3e_2026-09-30T08-26-40.343232.json,1790756610.888918,1 -v2anneal_120k,polymath_pt_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/08d5e9176e_2026-09-30T08-11-35.122166.json,1790754233.00453,1 -v2anneal_120k,sib200_als_Latn,0,lm-eval,vllm,,acc,none,0.27941176470588236,0.031493281045079584,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b38d397bad_2026-09-30T08-22-41.281427.json,1790756402.0516129,1 -v2anneal_120k,sib200_bos_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/84b0fb0940_2026-09-30T08-37-22.788656.json,1790757280.7902865,1 -v2anneal_120k,sib200_bul_Cyrl,0,lm-eval,vllm,,acc,none,0.4264705882352941,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/985293c9dd_2026-09-30T08-45-24.139562.json,1790757751.2152302,1 -v2anneal_120k,sib200_cat_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dd01a1f497_2026-09-30T08-49-11.320395.json,1790757994.1842062,1 -v2anneal_120k,sib200_ces_Latn,0,lm-eval,vllm,,acc,none,0.4019607843137255,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1022d1df8f_2026-09-30T07-44-37.987252.json,1790754113.7154791,1 -v2anneal_120k,sib200_dan_Latn,0,lm-eval,vllm,,acc,none,0.4166666666666667,0.03460228327239165,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/75ec6da525_2026-09-30T08-37-42.422062.json,1790757280.371878,1 -v2anneal_120k,sib200_deu_Latn,0,lm-eval,vllm,,acc,none,0.43137254901960786,0.034760990605016404,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7b90eeef8a_2026-09-30T08-22-48.020854.json,1790756406.4330118,1 -v2anneal_120k,sib200_ell_Grek,0,lm-eval,vllm,,acc,none,0.3382352941176471,0.03320574612945435,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550d859acb_2026-09-30T08-20-31.373051.json,1790756203.6818733,1 -v2anneal_120k,sib200_eng_Latn,0,lm-eval,vllm,,acc,none,0.43137254901960786,0.034760990605016404,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0659f8fd02_2026-09-30T08-32-51.994847.json,1790757008.9110518,1 -v2anneal_120k,sib200_est_Latn,0,lm-eval,vllm,,acc,none,0.38235294117647056,0.034107853389047135,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b467a6359f_2026-09-30T07-40-27.763149.json,1790753866.2138371,1 -v2anneal_120k,sib200_eus_Latn,0,lm-eval,vllm,,acc,none,0.3431372549019608,0.03332139944668079,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4e119efeba_2026-09-30T08-27-13.816666.json,1790756651.6482928,1 -v2anneal_120k,sib200_fin_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d979fe0f9e_2026-09-30T08-16-32.632646.json,1790756032.0031965,1 -v2anneal_120k,sib200_fra_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dec5329e1c_2026-09-30T07-34-37.559672.json,1790753511.3087628,1 -v2anneal_120k,sib200_gle_Latn,0,lm-eval,vllm,,acc,none,0.4362745098039216,0.03480693138457044,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60a7c70837_2026-09-30T08-42-18.127640.json,1790757572.4251707,1 -v2anneal_120k,sib200_glg_Latn,0,lm-eval,vllm,,acc,none,0.4117647058823529,0.03454236585380609,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1901771811_2026-09-30T08-21-02.284495.json,1790756302.7182622,1 -v2anneal_120k,sib200_hrv_Latn,0,lm-eval,vllm,,acc,none,0.38235294117647056,0.034107853389047135,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/afd8167157_2026-09-30T08-14-14.634576.json,1790755619.037115,1 -v2anneal_120k,sib200_hun_Latn,0,lm-eval,vllm,,acc,none,0.3333333333333333,0.033086111132364336,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fc4002c9d7_2026-09-30T08-52-51.406524.json,1790758208.7311106,1 -v2anneal_120k,sib200_isl_Latn,0,lm-eval,vllm,,acc,none,0.36764705882352944,0.0338413204567412,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/310da877a4_2026-09-30T08-38-51.226041.json,1790757372.4739983,1 -v2anneal_120k,sib200_ita_Latn,0,lm-eval,vllm,,acc,none,0.3284313725490196,0.03296245110172227,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f1b5f6c266_2026-09-30T08-38-57.051824.json,1790757376.0289724,1 -v2anneal_120k,sib200_kat_Geor,0,lm-eval,vllm,,acc,none,0.47549019607843135,0.035050931943487976,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e36f885401_2026-09-30T07-38-35.991544.json,1790753750.7517464,1 -v2anneal_120k,sib200_lit_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/452ca0845e_2026-09-30T08-22-45.376641.json,1790756401.2299142,1 -v2anneal_120k,sib200_lvs_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/05ff34b52f_2026-09-30T08-26-50.060445.json,1790756647.4421291,1 -v2anneal_120k,sib200_mkd_Cyrl,0,lm-eval,vllm,,acc,none,0.37254901960784315,0.03393388584958406,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/46d3c4fc72_2026-09-30T08-53-05.756592.json,1790758208.7756658,1 -v2anneal_120k,sib200_mlt_Latn,0,lm-eval,vllm,,acc,none,0.37254901960784315,0.03393388584958406,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f2907bd369_2026-09-30T07-40-29.392256.json,1790753866.0298214,1 -v2anneal_120k,sib200_nld_Latn,0,lm-eval,vllm,,acc,none,0.3627450980392157,0.0337449935631936,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1a7451919c_2026-09-30T08-20-40.030608.json,1790756203.7966251,1 -v2anneal_120k,sib200_nob_Latn,0,lm-eval,vllm,,acc,none,0.35294117647058826,0.033540924375915215,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed8bc71c08_2026-09-30T08-11-10.034827.json,1790754235.803487,1 -v2anneal_120k,sib200_pol_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b4906486d4_2026-09-30T07-40-50.037586.json,1790753866.62458,1 -v2anneal_120k,sib200_por_Latn,0,lm-eval,vllm,,acc,none,0.4362745098039216,0.03480693138457044,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/102b4d2167_2026-09-30T07-34-14.607890.json,1790753469.301372,1 -v2anneal_120k,sib200_ron_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78576cf6ae_2026-09-30T07-40-32.592661.json,1790753865.3778918,1 -v2anneal_120k,sib200_slk_Latn,0,lm-eval,vllm,,acc,none,0.36764705882352944,0.0338413204567412,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7fc4481f5b_2026-09-30T08-38-48.224315.json,1790757372.8077683,1 -v2anneal_120k,sib200_slv_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6508c69a1_2026-09-30T07-44-37.127181.json,1790754112.398617,1 -v2anneal_120k,sib200_spa_Latn,0,lm-eval,vllm,,acc,none,0.4117647058823529,0.03454236585380609,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3856e98830_2026-09-30T08-16-50.403991.json,1790756044.1519241,1 -v2anneal_120k,sib200_srp_Cyrl,0,lm-eval,vllm,,acc,none,0.4019607843137255,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dfe8fe4ce8_2026-09-30T07-34-14.844439.json,1790753469.4979644,1 -v2anneal_120k,sib200_swe_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b036b8da24_2026-09-30T07-40-22.728172.json,1790753866.3781729,1 -v2anneal_120k,sib200_tur_Latn,0,lm-eval,vllm,,acc,none,0.4264705882352941,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c7f2104b97_2026-09-30T07-42-27.448626.json,1790753985.941826,1 -v2anneal_120k,sib200_ukr_Cyrl,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e85261cdea_2026-09-30T08-39-04.286010.json,1790757380.7491508,1 -v2anneal_120k,social_iqa,0,lm-eval,vllm,,acc,none,0.529682702149437,0.011294116144908325,1954,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b410dc9345_2026-09-30T07-34-31.794303.json,1790753468.547855,1 -v2anneal_120k,squadv2,10,lm-eval,vllm,,HasAns_exact,none,80.3306342780027,,11873,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 -v2anneal_120k,squadv2,10,lm-eval,vllm,,HasAns_f1,none,86.54862172736328,,11873,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 -v2anneal_120k,squadv2,10,lm-eval,vllm,,NoAns_exact,none,0.0,,11873,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 -v2anneal_120k,squadv2,10,lm-eval,vllm,,NoAns_f1,none,0.0,,11873,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 -v2anneal_120k,squadv2,10,lm-eval,vllm,,best_exact,none,58.44352733091889,,11873,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 -v2anneal_120k,squadv2,10,lm-eval,vllm,,best_f1,none,59.64883767726625,,11873,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 -v2anneal_120k,squadv2,10,lm-eval,vllm,,exact,none,40.10780763075886,,11873,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 -v2anneal_120k,squadv2,10,lm-eval,vllm,,f1,none,43.212349835745776,,11873,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 -v2anneal_120k,winogrande,0,lm-eval,vllm,,acc,none,0.7190213101815311,0.012632541095875895,1267,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5e2c321f9a_2026-09-30T08-21-12.061404.json,1790756304.2532954,1 -v2anneal_120k,wsc273,0,lm-eval,vllm,,acc,none,0.8534798534798534,0.021441781058034026,273,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/53cda4f058_2026-09-30T08-29-16.068117.json,1790756790.8583784,1 -v2anneal_120k,xcopa:et,0,lighteval,hf/accelerate,,acc,none,0.65,0.021352091786223104,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e232988303/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-33-03.727328.json,1790753583.8088856,1 -v2anneal_120k,xcopa:it,0,lighteval,hf/accelerate,,acc,none,0.684,0.02081235951585585,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/82ecdec95b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-41-01.290183.json,1790754061.374489,1 -v2anneal_120k,xcopa:tr,0,lighteval,hf/accelerate,,acc,none,0.648,0.02138004238594606,500,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1cc83494eb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-33-03.728498.json,1790753583.81116,1 -v2anneal_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc,none,0.47,0.015790799515836725,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d2d5c2cc22_2026-09-30T08-32-38.152605.json,1790756982.5484955,1 -v2anneal_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc_norm,none,0.445,0.015723301886761007,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d2d5c2cc22_2026-09-30T08-32-38.152605.json,1790756982.5484955,1 -v2anneal_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc,none,0.644,0.015149042659306678,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/59ec13a078_2026-09-30T08-45-22.591132.json,1790757750.4307208,1 -v2anneal_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc_norm,none,0.618,0.015372453034968502,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/59ec13a078_2026-09-30T08-45-22.591132.json,1790757750.4307208,1 -v2anneal_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc,none,0.466,0.015782683329937694,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/03704b7c15_2026-09-30T08-10-59.172998.json,1790754223.6783261,1 -v2anneal_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc_norm,none,0.433,0.01567663091218125,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/03704b7c15_2026-09-30T08-10-59.172998.json,1790754223.6783261,1 -v2anneal_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc,none,0.487,0.015813952101896636,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f29465a9a6_2026-09-30T07-34-36.924944.json,1790753512.0613227,1 -v2anneal_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc_norm,none,0.434,0.015680876566375044,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f29465a9a6_2026-09-30T07-34-36.924944.json,1790753512.0613227,1 -v2anneal_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc,none,0.461,0.015771104201283047,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c9fb60d65_2026-09-30T08-47-38.218202.json,1790757888.217367,1 -v2anneal_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc_norm,none,0.432,0.015672320237336324,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c9fb60d65_2026-09-30T08-47-38.218202.json,1790757888.217367,1 -v2anneal_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc,none,0.396,0.015473313265859495,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7444a7ac74_2026-09-30T08-45-26.694718.json,1790757756.5939891,1 -v2anneal_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc_norm,none,0.378,0.015341165254026547,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7444a7ac74_2026-09-30T08-45-26.694718.json,1790757756.5939891,1 -v2anneal_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.459,0.015766025737882314,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/761634c7af_2026-09-30T08-52-24.622753.json,1790758111.541365,1 -v2anneal_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.44,0.015704987954361718,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/761634c7af_2026-09-30T08-52-24.622753.json,1790758111.541365,1 -v2anneal_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.461,0.015771104201283047,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/48a1da8d08_2026-09-30T07-40-37.787207.json,1790753866.2360377,1 -v2anneal_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.41,0.015560917136921659,1000,/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/48a1da8d08_2026-09-30T07-40-37.787207.json,1790753866.2360377,1 +v2anneal_120k,AIME24,0,Evalchemy,vllm,,accuracy_avg,,0.22000000000000003,0.008432740427115679,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/27b1296bac/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-41-17.133453.json,1790757672.5467868,1 +v2anneal_120k,AIME24,0,Evalchemy,vllm,,solved_avg,,6.6,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/27b1296bac/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-41-17.133453.json,1790757672.5467868,1 +v2anneal_120k,AIME25,0,Evalchemy,vllm,,accuracy_avg,,0.24,0.004216370213557838,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/28cc63de48/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-05-04.293807.json,1790759099.9904187,1 +v2anneal_120k,AIME25,0,Evalchemy,vllm,,solved_avg,,7.2,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/28cc63de48/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-05-04.293807.json,1790759099.9904187,1 +v2anneal_120k,AMC23,0,Evalchemy,vllm,,accuracy_avg,,0.39249999999999996,0.005062114182829147,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0554b99f8e/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-27-13.116020.json,1790756828.6413586,1 +v2anneal_120k,AMC23,0,Evalchemy,vllm,,solved_avg,,15.7,,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0554b99f8e/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-27-13.116020.json,1790756828.6413586,1 +v2anneal_120k,GPQADiamond,0,Evalchemy,vllm,,accuracy_avg,,0.3434343434343434,0.009523323652344071,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d346c086c7/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-50-00.687837.json,1790758194.75484,1 +v2anneal_120k,GPQADiamond,0,Evalchemy,vllm,,solved_avg,,68.0,,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d346c086c7/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-50-00.687837.json,1790758194.75484,1 +v2anneal_120k,HumanEval,0,Evalchemy,vllm,,python_pass@1,,0.25609756097560976,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/92c34ae84f/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T07-41-37.027671.json,1790754093.3926637,1 +v2anneal_120k,HumanEval,0,Evalchemy,vllm,,sh_pass@1,,0.012658227848101266,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/92c34ae84f/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T07-41-37.027671.json,1790754093.3926637,1 +v2anneal_120k,JEEBench,0,Evalchemy,vllm,,accuracy_avg,,0.2692556634304207,0.004624171574833398,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c51beb60f/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-08-56.095234.json,1790759332.2178957,1 +v2anneal_120k,JEEBench,0,Evalchemy,vllm,,solved_avg,,138.66666666666666,,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c51beb60f/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-08-56.095234.json,1790759332.2178957,1 +v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_avg,,0.19145466405740377,0.0024450965184594016,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 +v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_easy_avg,,0.4157509157509158,0.0027165562223793655,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 +v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_hard_avg,,0.0,0.0,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 +v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_medium_avg,,0.10760517799352749,0.004045307443365696,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 +v2anneal_120k,LiveCodeBench,0,Evalchemy,vllm,,solved_avg,,97.83333333333333,,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3200de0d0/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T09-13-46.322453.json,1790759622.8299491,1 +v2anneal_120k,MATH500,0,Evalchemy,vllm,,accuracy,,0.418,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b858c978b/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-35-09.998788.json,1790757305.6495829,1 +v2anneal_120k,MATH500,0,Evalchemy,vllm,,num_solved,,209,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b858c978b/__e__scratch__e-sta-openeurollm__vanosch1__flag-evals-test3__views__identity__v2anneal_120k/results_2026-09-30T08-35-09.998788.json,1790757305.6495829,1 +v2anneal_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc,none,0.2782608695652174,0.029614094221633747,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dc41e26809_2026-09-30T08-33-00.824285.json,1790757010.5143375,1 +v2anneal_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc_norm,none,0.25217391304347825,0.028696745294493314,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dc41e26809_2026-09-30T08-33-00.824285.json,1790757010.5143375,1 +v2anneal_120k,arc_challenge,10,lm-eval,vllm,,acc,none,0.6305460750853242,0.014104578366491963,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/51f856ea82_2026-09-30T08-26-38.967814.json,1790756611.5582352,1 +v2anneal_120k,arc_challenge,10,lm-eval,vllm,,acc_norm,none,0.6612627986348123,0.013830568927974365,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/51f856ea82_2026-09-30T08-26-38.967814.json,1790756611.5582352,1 +v2anneal_120k,arc_challenge,25,lm-eval,vllm,,acc,none,0.6390784982935154,0.014034761386175525,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge,25,lm-eval,vllm,,acc_norm,none,0.6680887372013652,0.01376098820088056,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc,none,0.5494880546075085,0.01453964609847157,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc_norm,none,0.5827645051194539,0.014409825518403108,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc,none,0.552901023890785,0.01452938016052677,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc_norm,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc,none,0.5477815699658704,0.014544519880633823,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc_norm,none,0.5802047781569966,0.014422181226303012,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc,none,0.5213310580204779,0.014598087973127125,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc_norm,none,0.5571672354948806,0.01451557387334892,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc,none,0.5187713310580204,0.01460109015063406,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc_norm,none,0.5631399317406144,0.014494421584256512,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc,none,0.575938566552901,0.014441889627464344,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc_norm,none,0.6194539249146758,0.014188277712349937,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc,none,0.5093856655290102,0.014608816322065041,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc_norm,none,0.523037542662116,0.014595873205358168,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc,none,0.4803754266211604,0.014600132075947018,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc_norm,none,0.5315699658703071,0.014582236460866984,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc,none,0.5699658703071673,0.01446763155913799,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc_norm,none,0.60580204778157,0.014280522667467148,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc,none,0.5042662116040956,0.014610858923956936,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc_norm,none,0.5452218430034129,0.014551507060836232,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc,none,0.49573378839590443,0.014610858923956936,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc_norm,none,0.5298634812286689,0.014585305840007116,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc,none,0.5708191126279863,0.014464085894870677,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc_norm,none,0.6023890784982935,0.014301752223279514,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc,none,0.5349829351535836,0.014575583922019714,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc_norm,none,0.5546075085324232,0.014523987638344072,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc,none,0.515358361774744,0.014604496129394757,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc_norm,none,0.5392491467576792,0.014566303676636534,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc,none,0.5418088737201365,0.014560220308714553,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc_norm,none,0.5750853242320819,0.014445698968520807,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc,none,0.5392491467576792,0.014566303676636534,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc_norm,none,0.5656996587030717,0.014484703048857371,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc,none,0.537542662116041,0.014570144495075503,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc_norm,none,0.5537542662116041,0.014526705548539945,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc_norm,none,0.621160409556314,0.01417591549000027,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc,none,0.5563139931740614,0.014518421825670504,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc_norm,none,0.5878839590443686,0.014383915302225435,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc,none,0.5503412969283277,0.014537144444284783,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc_norm,none,0.5784982935153583,0.014430197069326087,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc,none,0.5349829351535836,0.014575583922019714,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc_norm,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc,none,0.5349829351535836,0.014575583922019714,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc_norm,none,0.5827645051194539,0.014409825518403108,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-15-57.437448.json,1790808085.8357077,1 +v2anneal_120k,arc_easy,10,lm-eval,vllm,,acc,none,0.8691077441077442,0.006920890518900526,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2d96d78293_2026-09-30T08-43-31.066314.json,1790757595.9904432,1 +v2anneal_120k,arc_easy,10,lm-eval,vllm,,acc_norm,none,0.8796296296296297,0.006676946806414794,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2d96d78293_2026-09-30T08-43-31.066314.json,1790757595.9904432,1 +v2anneal_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc,none,0.8944444444444445,0.010247959196000194,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/613b0f3dfe_2026-09-30T07-34-54.848787.json,1790753516.9584126,1 +v2anneal_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc_norm,none,0.8944444444444445,0.010247959196000194,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/613b0f3dfe_2026-09-30T07-34-54.848787.json,1790753516.9584126,1 +v2anneal_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc,none,0.9077777777777778,0.009650009016958635,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6a8c6fb64f_2026-09-30T08-14-38.321906.json,1790755618.6065273,1 +v2anneal_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc_norm,none,0.9077777777777778,0.009650009016958635,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6a8c6fb64f_2026-09-30T08-14-38.321906.json,1790755618.6065273,1 +v2anneal_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8499de27b5_2026-09-30T07-44-55.489804.json,1790754113.7732503,1 +v2anneal_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc_norm,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8499de27b5_2026-09-30T07-44-55.489804.json,1790754113.7732503,1 +v2anneal_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/45935620da_2026-09-30T07-42-41.324231.json,1790753987.35326,1 +v2anneal_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc_norm,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/45935620da_2026-09-30T07-42-41.324231.json,1790753987.35326,1 +v2anneal_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8107e3c5e4_2026-09-30T08-20-49.335447.json,1790756205.6269324,1 +v2anneal_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc_norm,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8107e3c5e4_2026-09-30T08-20-49.335447.json,1790756205.6269324,1 +v2anneal_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc,none,0.9322222222222222,0.008383464750361901,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ea0903b3ae_2026-09-30T08-37-33.320814.json,1790757281.0689347,1 +v2anneal_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc_norm,none,0.9322222222222222,0.008383464750361901,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ea0903b3ae_2026-09-30T08-37-33.320814.json,1790757281.0689347,1 +v2anneal_120k,belebele_est_Latn,5,lm-eval,vllm,,acc,none,0.8777777777777778,0.010924146933565216,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/04aea63d6a_2026-09-30T07-34-31.286385.json,1790753469.2925987,1 +v2anneal_120k,belebele_est_Latn,5,lm-eval,vllm,,acc_norm,none,0.8777777777777778,0.010924146933565216,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/04aea63d6a_2026-09-30T07-34-31.286385.json,1790753469.2925987,1 +v2anneal_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc,none,0.8833333333333333,0.010706705536407178,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c805fed593_2026-09-30T08-37-40.708380.json,1790757279.8233929,1 +v2anneal_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc_norm,none,0.8833333333333333,0.010706705536407178,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c805fed593_2026-09-30T08-37-40.708380.json,1790757279.8233929,1 +v2anneal_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc,none,0.9166666666666666,0.009217969157169261,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/33a8c0cba3_2026-09-30T08-27-09.656549.json,1790756643.080764,1 +v2anneal_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc_norm,none,0.9166666666666666,0.009217969157169261,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/33a8c0cba3_2026-09-30T08-27-09.656549.json,1790756643.080764,1 +v2anneal_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc,none,0.8844444444444445,0.010662298780233998,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f781842a99_2026-09-30T08-47-51.193601.json,1790757887.8456812,1 +v2anneal_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc_norm,none,0.8844444444444445,0.010662298780233998,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f781842a99_2026-09-30T08-47-51.193601.json,1790757887.8456812,1 +v2anneal_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3bf2964e48_2026-09-30T08-17-02.646892.json,1790756046.3326223,1 +v2anneal_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc_norm,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3bf2964e48_2026-09-30T08-17-02.646892.json,1790756046.3326223,1 +v2anneal_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3a159b4c87_2026-09-30T08-17-15.343677.json,1790756046.335199,1 +v2anneal_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc_norm,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3a159b4c87_2026-09-30T08-17-15.343677.json,1790756046.335199,1 +v2anneal_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7664f00e89_2026-09-30T08-52-30.676840.json,1790758109.0038042,1 +v2anneal_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc_norm,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7664f00e89_2026-09-30T08-52-30.676840.json,1790758109.0038042,1 +v2anneal_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1d4aaac975_2026-09-30T08-27-09.934934.json,1790756652.7021835,1 +v2anneal_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc_norm,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1d4aaac975_2026-09-30T08-27-09.934934.json,1790756652.7021835,1 +v2anneal_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5cafe66f64_2026-09-30T07-34-25.177521.json,1790753469.394227,1 +v2anneal_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc_norm,none,0.8766666666666667,0.010966742231624015,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5cafe66f64_2026-09-30T07-34-25.177521.json,1790753469.394227,1 +v2anneal_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.010481480680812848,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c5a24491f_2026-09-30T08-36-39.689261.json,1790757138.5261528,1 +v2anneal_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc_norm,none,0.8888888888888888,0.010481480680812848,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c5a24491f_2026-09-30T08-36-39.689261.json,1790757138.5261528,1 +v2anneal_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6cfede2de_2026-09-30T08-43-40.609122.json,1790757623.3662093,1 +v2anneal_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc_norm,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6cfede2de_2026-09-30T08-43-40.609122.json,1790757623.3662093,1 +v2anneal_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9ed7ef48b2_2026-09-30T07-40-47.590000.json,1790753866.4226592,1 +v2anneal_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc_norm,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9ed7ef48b2_2026-09-30T07-40-47.590000.json,1790753866.4226592,1 +v2anneal_120k,belebele_por_Latn,5,lm-eval,vllm,,acc,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d96ffe17ac_2026-09-30T08-27-13.949496.json,1790756652.0558429,1 +v2anneal_120k,belebele_por_Latn,5,lm-eval,vllm,,acc_norm,none,0.8977777777777778,0.010103625463371327,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d96ffe17ac_2026-09-30T08-27-13.949496.json,1790756652.0558429,1 +v2anneal_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc,none,0.9044444444444445,0.009804807528775588,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6c806908d3_2026-09-30T07-42-49.499385.json,1790753987.0305846,1 +v2anneal_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc_norm,none,0.9044444444444445,0.009804807528775588,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6c806908d3_2026-09-30T07-42-49.499385.json,1790753987.0305846,1 +v2anneal_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc,none,0.8933333333333333,0.010295354033282278,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/01a47b8165_2026-09-30T07-34-51.551218.json,1790753511.7604973,1 +v2anneal_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc_norm,none,0.8933333333333333,0.010295354033282278,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/01a47b8165_2026-09-30T07-34-51.551218.json,1790753511.7604973,1 +v2anneal_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c201cc0f3f_2026-09-30T07-40-53.615461.json,1790753873.9768434,1 +v2anneal_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc_norm,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c201cc0f3f_2026-09-30T07-40-53.615461.json,1790753873.9768434,1 +v2anneal_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6addf594cf_2026-09-30T07-40-46.872580.json,1790753866.0631695,1 +v2anneal_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc_norm,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6addf594cf_2026-09-30T07-40-46.872580.json,1790753866.0631695,1 +v2anneal_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc,none,0.8855555555555555,0.010617576963634174,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a987d2decb_2026-09-30T08-14-26.337113.json,1790755617.4652393,1 +v2anneal_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc_norm,none,0.8855555555555555,0.010617576963634174,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a987d2decb_2026-09-30T08-14-26.337113.json,1790755617.4652393,1 +v2anneal_120k,bigbench_cs_algorithms_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7818181818181819,0.011372076264788566,1320,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/45e5c4e471_2026-09-30T16-51-22.331879.json,1790786897.8896616,1 +v2anneal_120k,bigbench_dyck_languages_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.636,0.015222868840522022,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c9d8f057ca_2026-09-30T07-35-00.931103.json,1790753514.1676912,1 +v2anneal_120k,bigbench_language_identification_multiple_choice,10,lm-eval,vllm,,acc,none,0.2629,0.004402305876436003,10000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0d6d9413fa_2026-09-30T09-11-48.610799.json,1790755619.9956675,1 +v2anneal_120k,bigbench_operators_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.8285714285714286,0.026069544122384443,210,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c364babeaf_2026-09-30T07-42-43.932264.json,1790753986.5193744,1 +v2anneal_120k,bigbench_qa_wikidata_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7232419664386596,0.003138557397975128,20321,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3073f1e8f6_2026-09-30T08-41-26.495060.json,1790757384.0517612,1 +v2anneal_120k,bigbench_repeat_copy_logic_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.65625,0.08530513305661301,32,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f8e047b339_2026-09-30T08-10-56.455424.json,1790754227.1787226,1 +v2anneal_120k,boolq,10,lm-eval,vllm,,acc,none,0.864525993883792,0.005985625684183008,3270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d015723bc4_2026-09-30T07-43-28.095124.json,1790753864.779276,1 +v2anneal_120k,commonsense_qa,10,lm-eval,vllm,,acc,none,0.8263718263718264,0.01084470978346005,1221,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/52b57f11d3_2026-09-30T08-33-21.133337.json,1790757011.7022827,1 +v2anneal_120k,copa,0,lm-eval,vllm,,acc,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a9afe81490_2026-09-30T07-38-31.073944.json,1790753750.935608,1 +v2anneal_120k,coqa,0,lm-eval,vllm,,em,none,0.7075,0.016618961452495126,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8a8c6d6016_2026-09-30T08-14-35.743007.json,1790755618.6579852,1 +v2anneal_120k,coqa,0,lm-eval,vllm,,f1,none,0.8275709618300378,0.011891552197371301,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8a8c6d6016_2026-09-30T08-14-35.743007.json,1790755618.6579852,1 +v2anneal_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.49580368982227,0.017873768942221237,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/97856f122e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-58.405051.json,1790755604.83264,1 +v2anneal_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7118872153187481,0.003838496595288138,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/97856f122e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-58.405051.json,1790755604.83264,1 +v2anneal_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2712393810193638,0.006100325037255695,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/97856f122e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-58.405051.json,1790755604.83264,1 +v2anneal_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.43463242062653,0.011983123071398632,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/97856f122e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-58.405051.json,1790755604.83264,1 +v2anneal_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.0837927584148,0.01900944324996355,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/62d25d021e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-42.466835.json,1790753923.444419,1 +v2anneal_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7152651854832485,0.003807541510780792,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/62d25d021e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-42.466835.json,1790753923.444419,1 +v2anneal_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28457543007268465,0.006312256117436793,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/62d25d021e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-42.466835.json,1790753923.444419,1 +v2anneal_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.32752519730818,0.011885459416232843,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/62d25d021e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-42.466835.json,1790753923.444419,1 +v2anneal_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.42367496389634,0.01741317195765659,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6a7be9ecd8/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-37.582841.json,1790753798.71417,1 +v2anneal_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7045446152034913,0.00393158895434034,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6a7be9ecd8/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-37.582841.json,1790753798.71417,1 +v2anneal_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2641951550601192,0.006118162950569426,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6a7be9ecd8/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-37.582841.json,1790753798.71417,1 +v2anneal_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.34228727089832,0.011576837204037784,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6a7be9ecd8/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-37.582841.json,1790753798.71417,1 +v2anneal_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,49.90526944339191,0.019459720639379043,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2fac1223dc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-44.748260.json,1790754045.580605,1 +v2anneal_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7376749653756199,0.0039500704346317975,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2fac1223dc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-44.748260.json,1790754045.580605,1 +v2anneal_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.32819516532560894,0.007037623120173013,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2fac1223dc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-44.748260.json,1790754045.580605,1 +v2anneal_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.68782589373826,0.012867514415585816,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2fac1223dc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-44.748260.json,1790754045.580605,1 +v2anneal_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.306161372283775,0.017919427535563137,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5802d24f50/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-13.032007.json,1790755604.832521,1 +v2anneal_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6930665209153473,0.004047831200697218,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5802d24f50/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-13.032007.json,1790755604.832521,1 +v2anneal_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2624424313890465,0.006277519586993478,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5802d24f50/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-13.032007.json,1790755604.832521,1 +v2anneal_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.05500987803457,0.012484208859652502,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5802d24f50/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-13.032007.json,1790755604.832521,1 +v2anneal_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,52.07458177483599,0.01954214599031202,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/868240b59e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-48.489108.json,1790753929.638437,1 +v2anneal_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7521626757288533,0.003963678025629041,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/868240b59e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-48.489108.json,1790753929.638437,1 +v2anneal_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3526253126244304,0.006854576306568215,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/868240b59e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-48.489108.json,1790753929.638437,1 +v2anneal_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.34284067643034,0.012926175023147923,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/868240b59e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-48.489108.json,1790753929.638437,1 +v2anneal_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.77153746557002,0.019997646277299157,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/83acc65062/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-19.329270.json,1790754320.5156,1 +v2anneal_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7199822560808736,0.003946190126963025,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/83acc65062/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-19.329270.json,1790754320.5156,1 +v2anneal_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29303849374333246,0.006638864326959291,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/83acc65062/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-19.329270.json,1790754320.5156,1 +v2anneal_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.54310382172478,0.01318103809292999,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/83acc65062/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-19.329270.json,1790754320.5156,1 +v2anneal_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.24450193449369,0.018418504777938455,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/da34212f99/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-06.030421.json,1790753826.896236,1 +v2anneal_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6604099366023057,0.004243523631815729,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/da34212f99/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-06.030421.json,1790753826.896236,1 +v2anneal_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22491076407610824,0.005875695156917328,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/da34212f99/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-06.030421.json,1790753826.896236,1 +v2anneal_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.82389474922735,0.013334127748540073,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/da34212f99/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-06.030421.json,1790753826.896236,1 +v2anneal_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu,none,34.34810837932732,0.015673249846027575,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/100817f5f2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-13.796090.json,1790755935.010898,1 +v2anneal_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6266520773549422,0.0037974043804741156,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/100817f5f2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-13.796090.json,1790755935.010898,1 +v2anneal_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18119622387295137,0.004817695652105389,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/100817f5f2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-13.796090.json,1790755935.010898,1 +v2anneal_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.24570032843578,0.010872700638926718,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/100817f5f2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-13.796090.json,1790755935.010898,1 +v2anneal_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu,none,32.44275166580018,0.01708217833414928,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d4a137fd18/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-49.753349.json,1790754350.573568,1 +v2anneal_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5993013544757751,0.004469414487816768,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d4a137fd18/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-49.753349.json,1790754350.573568,1 +v2anneal_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1682303383767639,0.005017110312991332,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d4a137fd18/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-49.753349.json,1790754350.573568,1 +v2anneal_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.238709746920456,0.011808811167419369,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d4a137fd18/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-49.753349.json,1790754350.573568,1 +v2anneal_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu,none,40.977533762594234,0.018242374089000462,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/742bd88dc6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-00.111172.json,1790753820.951066,1 +v2anneal_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6603498488209074,0.004036848408145262,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/742bd88dc6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-00.111172.json,1790753820.951066,1 +v2anneal_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.22761679177035632,0.005552314488177307,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/742bd88dc6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-00.111172.json,1790753820.951066,1 +v2anneal_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,64.56087793380667,0.012158827122996733,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/742bd88dc6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-00.111172.json,1790753820.951066,1 +v2anneal_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu,none,43.94335458619114,0.01840736887597285,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c89ad84608/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-52.201792.json,1790787233.013158,1 +v2anneal_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6776344541062229,0.004247519045625766,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c89ad84608/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-52.201792.json,1790787233.013158,1 +v2anneal_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.27206862365596923,0.006205343274531046,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c89ad84608/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-52.201792.json,1790787233.013158,1 +v2anneal_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.28053789603096,0.013080664164927223,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c89ad84608/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-52.201792.json,1790787233.013158,1 +v2anneal_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu,none,33.19507600380193,0.019967403691796542,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f137d087be/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-14.620535.json,1790787195.418929,1 +v2anneal_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5925897258332335,0.004999658943907772,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f137d087be/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-14.620535.json,1790787195.418929,1 +v2anneal_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17499534461243696,0.005903880028179754,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f137d087be/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-14.620535.json,1790787195.418929,1 +v2anneal_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.04064560293918,0.014352815200572872,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f137d087be/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-14.620535.json,1790787195.418929,1 +v2anneal_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu,none,48.24650963253074,0.019991003571247386,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1f67b2d42b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-49.045074.json,1790753930.044486,1 +v2anneal_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7103266641590754,0.004446787475179131,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1f67b2d42b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-49.045074.json,1790753930.044486,1 +v2anneal_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.32011268264551596,0.007182919511333117,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1f67b2d42b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-49.045074.json,1790753930.044486,1 +v2anneal_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.99200396470036,0.012742183241793886,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1f67b2d42b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-49.045074.json,1790753930.044486,1 +v2anneal_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu,none,40.3284618211959,0.021793380199684662,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/782ee0535a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-42-35.179678.json,1790754156.154241,1 +v2anneal_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6520394512492752,0.004760723708908364,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/782ee0535a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-42-35.179678.json,1790754156.154241,1 +v2anneal_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23916561451070997,0.006652813835001809,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/782ee0535a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-42-35.179678.json,1790754156.154241,1 +v2anneal_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.71229578057241,0.014537540107628538,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/782ee0535a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-42-35.179678.json,1790754156.154241,1 +v2anneal_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu,none,26.722934187458257,0.01483519493786614,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d6616a05f6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-12.192110.json,1790753953.082434,1 +v2anneal_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_1,none,0.535306595896592,0.004457396447240381,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d6616a05f6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-12.192110.json,1790753953.082434,1 +v2anneal_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_4,none,0.12468133087399706,0.004055284960251834,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d6616a05f6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-12.192110.json,1790753953.082434,1 +v2anneal_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,chrf++,rescored,51.00912754856832,0.012682127454018725,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d6616a05f6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-12.192110.json,1790753953.082434,1 +v2anneal_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu,none,27.04193752782002,0.01893830358741019,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/87bd680b8b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-36.327923.json,1790753857.186767,1 +v2anneal_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5545080960179309,0.005091752878951199,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/87bd680b8b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-36.327923.json,1790753857.186767,1 +v2anneal_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12737340838451433,0.005329779687111957,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/87bd680b8b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-36.327923.json,1790753857.186767,1 +v2anneal_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.98100090404032,0.013432752238009833,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/87bd680b8b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-36.327923.json,1790753857.186767,1 +v2anneal_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu,none,19.017225953764598,0.016448588926211965,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b9871a2774/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-14.199749.json,1790755935.39876,1 +v2anneal_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.48658554524018605,0.004723198957426475,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b9871a2774/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-14.199749.json,1790755935.39876,1 +v2anneal_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.07534446340487928,0.00403695281589065,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b9871a2774/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-14.199749.json,1790755935.39876,1 +v2anneal_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,52.01409233452421,0.012258078254741593,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b9871a2774/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-14.199749.json,1790755935.39876,1 +v2anneal_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu,none,25.28029146372687,0.018862396009194125,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf58aa3504/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-03.805065.json,1790755604.832239,1 +v2anneal_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5253447605478087,0.005212699492775908,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf58aa3504/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-03.805065.json,1790755604.832239,1 +v2anneal_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11615325833822131,0.0051361713817452866,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf58aa3504/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-03.805065.json,1790755604.832239,1 +v2anneal_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.2619176675131,0.012765988257010296,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf58aa3504/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-03.805065.json,1790755604.832239,1 +v2anneal_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu,none,51.437044559979796,0.023397362574870278,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6ae4fdcb21/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-39.504974.json,1790754040.345049,1 +v2anneal_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7039715962556076,0.004965053434555822,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6ae4fdcb21/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-39.504974.json,1790754040.345049,1 +v2anneal_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.36765640656952586,0.008097418223210674,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6ae4fdcb21/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-39.504974.json,1790754040.345049,1 +v2anneal_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.15634898947863,0.015595454506079461,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/6ae4fdcb21/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-39.504974.json,1790754040.345049,1 +v2anneal_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu,none,30.38059405518762,0.018043960529600268,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f64b93f7bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.383552.json,1790755933.598349,1 +v2anneal_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5732688810364633,0.004567025939936597,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f64b93f7bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.383552.json,1790755933.598349,1 +v2anneal_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.15546043454523317,0.0051111730280654155,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f64b93f7bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.383552.json,1790755933.598349,1 +v2anneal_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.20388049578169,0.013667735602082568,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f64b93f7bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.383552.json,1790755933.598349,1 +v2anneal_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu,none,37.292359089171015,0.016269411717259426,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/39477b29a6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-38.980260.json,1790753920.263699,1 +v2anneal_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6408040848328898,0.0037472821379716183,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/39477b29a6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-38.980260.json,1790753920.263699,1 +v2anneal_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20900268231538094,0.00542243395325613,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/39477b29a6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-38.980260.json,1790753920.263699,1 +v2anneal_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.10011626842501,0.010838764463706421,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/39477b29a6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-38.980260.json,1790753920.263699,1 +v2anneal_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.914863156008273,0.019470083119627644,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3c6e6078ce/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-16.146249.json,1790755936.988646,1 +v2anneal_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5776683581932528,0.00499144370529589,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3c6e6078ce/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-16.146249.json,1790755936.988646,1 +v2anneal_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1661789724637024,0.005539426265331667,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3c6e6078ce/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-16.146249.json,1790755936.988646,1 +v2anneal_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.38864956997195,0.013834303997904395,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3c6e6078ce/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-16.146249.json,1790755936.988646,1 +v2anneal_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu,none,26.203875784161635,0.017904273605822658,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71d5d8c30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-55.643818.json,1790753876.458679,1 +v2anneal_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5568536121165085,0.004387278061870514,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71d5d8c30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-55.643818.json,1790753876.458679,1 +v2anneal_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11010147312298672,0.004284230679638809,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71d5d8c30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-55.643818.json,1790753876.458679,1 +v2anneal_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.62700259181234,0.012105681372653592,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71d5d8c30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-55.643818.json,1790753876.458679,1 +v2anneal_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu,none,28.308020085529474,0.019836388925355077,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d9dbb473d1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-40.085809.json,1790753860.921484,1 +v2anneal_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.539677720527927,0.0049180499389946605,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d9dbb473d1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-40.085809.json,1790753860.921484,1 +v2anneal_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1420727850523423,0.005378353173830976,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d9dbb473d1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-40.085809.json,1790753860.921484,1 +v2anneal_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,52.53371289612861,0.014519112035408436,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d9dbb473d1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-40.085809.json,1790753860.921484,1 +v2anneal_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu,none,32.43650110038292,0.014847283970080904,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0df7149da6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-45.730797.json,1790753807.241788,1 +v2anneal_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5940355060149777,0.0038031060668150597,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0df7149da6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-45.730797.json,1790753807.241788,1 +v2anneal_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16404111384842315,0.004190850645763976,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0df7149da6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-45.730797.json,1790753807.241788,1 +v2anneal_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.856350640573794,0.010226265067883239,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0df7149da6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-45.730797.json,1790753807.241788,1 +v2anneal_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu,none,3.6510066586646763,0.007230547759205677,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cddef4a943/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-39-40.528888.json,1790757581.086417,1 +v2anneal_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_1,none,0.22312185261551548,0.0040433214907522564,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cddef4a943/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-39-40.528888.json,1790757581.086417,1 +v2anneal_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_4,none,0.005980471872460149,0.0009257656166834676,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cddef4a943/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-39-40.528888.json,1790757581.086417,1 +v2anneal_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,chrf++,rescored,26.967176626606914,0.00961829563172114,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cddef4a943/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-39-40.528888.json,1790757581.086417,1 +v2anneal_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu,none,26.63099599780555,0.01965041988502942,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b623591db4/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-07.585462.json,1790787248.378122,1 +v2anneal_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5440562083797443,0.00506520640228864,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b623591db4/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-07.585462.json,1790787248.378122,1 +v2anneal_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12574840988146457,0.005185630972930373,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b623591db4/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-07.585462.json,1790787248.378122,1 +v2anneal_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.58147783640398,0.013731914055818716,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b623591db4/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-07.585462.json,1790787248.378122,1 +v2anneal_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu,none,31.41956023085231,0.01966182777923508,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/60377d430a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-16.378583.json,1790754017.600008,1 +v2anneal_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.591530405522697,0.005211799547104305,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/60377d430a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-16.378583.json,1790754017.600008,1 +v2anneal_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16726250061385084,0.006295512472582018,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/60377d430a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-16.378583.json,1790754017.600008,1 +v2anneal_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.772593442124744,0.014330847238355064,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/60377d430a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-16.378583.json,1790754017.600008,1 +v2anneal_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu,none,35.948434858408184,0.01712441088605186,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/811d352406/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-42.841112.json,1790753864.023363,1 +v2anneal_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6291440753651142,0.0039286277319916995,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/811d352406/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-42.841112.json,1790753864.023363,1 +v2anneal_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.19068255387190997,0.005074844590141389,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/811d352406/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-42.841112.json,1790753864.023363,1 +v2anneal_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,61.80757771603616,0.01139594714054676,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/811d352406/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-42.841112.json,1790753864.023363,1 +v2anneal_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu,none,39.81325432987597,0.019474183513544588,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf35b1f259/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-15.146608.json,1790754315.973067,1 +v2anneal_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6518743194398726,0.004669348639634521,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf35b1f259/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-15.146608.json,1790754315.973067,1 +v2anneal_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23676608501773977,0.006543879552104657,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf35b1f259/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-15.146608.json,1790754315.973067,1 +v2anneal_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.83181844585137,0.013570389571438022,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/bf35b1f259/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-15.146608.json,1790754315.973067,1 +v2anneal_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu,none,28.258407528723023,0.016400869958964597,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/af46d37edf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-08.673828.json,1790753829.531919,1 +v2anneal_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5791834751000696,0.004332622471820654,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/af46d37edf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-08.673828.json,1790753829.531919,1 +v2anneal_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1310919790194132,0.004535474074649744,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/af46d37edf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-08.673828.json,1790753829.531919,1 +v2anneal_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.291593197460934,0.011776753917940525,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/af46d37edf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-08.673828.json,1790753829.531919,1 +v2anneal_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu,none,34.24295360309306,0.015618936952799221,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/4d2a380287/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-43.693963.json,1790753804.485438,1 +v2anneal_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6132380607421881,0.0037918610297687947,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/4d2a380287/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-43.693963.json,1790753804.485438,1 +v2anneal_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16947512140679397,0.004482663331885258,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/4d2a380287/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-43.693963.json,1790753804.485438,1 +v2anneal_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.97515002289126,0.010774043539282019,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/4d2a380287/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-43.693963.json,1790753804.485438,1 +v2anneal_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu,none,22.542720524534232,0.016334239809939807,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/8b1db287a7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-39.180462.json,1790753800.301554,1 +v2anneal_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.49873710245198694,0.004634418977591393,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/8b1db287a7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-39.180462.json,1790753800.301554,1 +v2anneal_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.09677448140886817,0.00412668462400495,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/8b1db287a7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-39.180462.json,1790753800.301554,1 +v2anneal_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,49.326547210138365,0.012305609815876906,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/8b1db287a7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-39.180462.json,1790753800.301554,1 +v2anneal_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu,none,50.01801630450886,0.02085842614303581,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/652022919b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-06.169464.json,1790753947.784885,1 +v2anneal_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7258543146916152,0.004489579634100495,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/652022919b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-06.169464.json,1790753947.784885,1 +v2anneal_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3378748684347292,0.007521553933890442,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/652022919b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-06.169464.json,1790753947.784885,1 +v2anneal_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.86996858985057,0.013644518484891012,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/652022919b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-06.169464.json,1790753947.784885,1 +v2anneal_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu,none,40.724795465499504,0.018535565825811697,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f057e31b81/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-26.008788.json,1790753846.865132,1 +v2anneal_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6507707425824585,0.004515391084555917,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f057e31b81/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-26.008788.json,1790753846.865132,1 +v2anneal_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2498325580898546,0.00624045249301115,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f057e31b81/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-26.008788.json,1790753846.865132,1 +v2anneal_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.11015168428755,0.012773885283956583,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f057e31b81/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-26.008788.json,1790753846.865132,1 +v2anneal_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu,none,34.002466404683275,0.020475189790038026,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0e1f710903/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-45.790602.json,1790753987.2999,1 +v2anneal_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5955473965296862,0.005183263487083542,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0e1f710903/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-45.790602.json,1790753987.2999,1 +v2anneal_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18765284888117387,0.006135999674867611,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0e1f710903/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-45.790602.json,1790753987.2999,1 +v2anneal_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.10325192995245,0.014302501611674547,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0e1f710903/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-45.790602.json,1790753987.2999,1 +v2anneal_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.308954244231618,0.018278791569936025,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cf92330f71/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-12.581794.json,1790787193.625231,1 +v2anneal_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.58351468096674,0.004956098934879901,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cf92330f71/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-12.581794.json,1790787193.625231,1 +v2anneal_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16723634939159115,0.0055553764891342035,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cf92330f71/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-12.581794.json,1790787193.625231,1 +v2anneal_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.11508603256207,0.013353601835866242,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/cf92330f71/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-12.581794.json,1790787193.625231,1 +v2anneal_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu,none,29.421266555066232,0.013476687986262394,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d726069b65/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-24.942585.json,1790787265.771125,1 +v2anneal_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5790852947910196,0.0035626562308184065,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d726069b65/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-24.942585.json,1790787265.771125,1 +v2anneal_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.13999310452242858,0.003731219206267395,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d726069b65/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-24.942585.json,1790787265.771125,1 +v2anneal_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.790710672646,0.010139415948893928,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d726069b65/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-54-24.942585.json,1790787265.771125,1 +v2anneal_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu,none,34.6986316113732,0.018381483148175448,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/677c7d2a5b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-35.718156.json,1790753976.917203,1 +v2anneal_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6107355665598778,0.004676663359228811,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/677c7d2a5b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-35.718156.json,1790753976.917203,1 +v2anneal_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.18942250262607296,0.0056823986083420625,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/677c7d2a5b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-35.718156.json,1790753976.917203,1 +v2anneal_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,59.01492077195102,0.01306819966611672,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/677c7d2a5b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-35.718156.json,1790753976.917203,1 +v2anneal_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu,none,46.51667668615471,0.019646228641442397,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f47a1d69bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-49.978716.json,1790753810.825692,1 +v2anneal_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6930778304202803,0.004403820399261887,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f47a1d69bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-49.978716.json,1790753810.825692,1 +v2anneal_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29622339461399244,0.0067583181061484894,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f47a1d69bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-49.978716.json,1790753810.825692,1 +v2anneal_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.83887909826146,0.013076088486436559,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/f47a1d69bf/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-49.978716.json,1790753810.825692,1 +v2anneal_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu,none,25.675682575077705,0.01886822783850094,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d57d6d77fc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-01.610695.json,1790753822.442255,1 +v2anneal_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5435408370237054,0.004964088407358119,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d57d6d77fc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-01.610695.json,1790753822.442255,1 +v2anneal_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1208401211699128,0.005053024895010905,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d57d6d77fc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-01.610695.json,1790753822.442255,1 +v2anneal_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.43194435194783,0.013448661636411197,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d57d6d77fc/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-37-01.610695.json,1790753822.442255,1 +v2anneal_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu,none,30.348223283687727,0.01835249338589849,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/efb928f4d3/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.995737.json,1790755934.084875,1 +v2anneal_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.5572183553655581,0.00492587915523367,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/efb928f4d3/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.995737.json,1790755934.084875,1 +v2anneal_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.15076461683115433,0.005059098560793833,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/efb928f4d3/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.995737.json,1790755934.084875,1 +v2anneal_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,55.44925556557193,0.013399291688297565,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/efb928f4d3/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-12.995737.json,1790755934.084875,1 +v2anneal_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.074487127638115,0.019369789256980595,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b615bcadf2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-32.950066.json,1790753913.743139,1 +v2anneal_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6747726150556571,0.004240336833844642,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b615bcadf2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-32.950066.json,1790753913.743139,1 +v2anneal_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2323149584026767,0.0061818177647449,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b615bcadf2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-32.950066.json,1790753913.743139,1 +v2anneal_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.731040604969145,0.013222352343258418,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b615bcadf2/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-32.950066.json,1790753913.743139,1 +v2anneal_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.29981317709041,0.01856489307447493,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0116a54194/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-41.960894.json,1790753982.955544,1 +v2anneal_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.62883864185062,0.004370637056121874,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0116a54194/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-41.960894.json,1790753982.955544,1 +v2anneal_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18633328699304788,0.005696350283259595,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0116a54194/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-41.960894.json,1790753982.955544,1 +v2anneal_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.04311154978908,0.013335242267227427,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0116a54194/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-41.960894.json,1790753982.955544,1 +v2anneal_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.407741486381816,0.01797126049931097,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d646b2f30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-30.208122.json,1790754271.06476,1 +v2anneal_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.655419615634274,0.0042794860469791965,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d646b2f30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-30.208122.json,1790754271.06476,1 +v2anneal_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21033837291085822,0.005890855551182566,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d646b2f30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-30.208122.json,1790754271.06476,1 +v2anneal_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.781438759198906,0.012722435064938295,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d646b2f30a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-30.208122.json,1790754271.06476,1 +v2anneal_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,48.53839164339867,0.02108617852272175,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d35b3d22f1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-00.279514.json,1790753941.114493,1 +v2anneal_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7297896736942243,0.004318623167354128,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d35b3d22f1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-00.279514.json,1790753941.114493,1 +v2anneal_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3225457889352582,0.007230214420901475,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d35b3d22f1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-00.279514.json,1790753941.114493,1 +v2anneal_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.5529485721811,0.014198648475060015,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/d35b3d22f1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-00.279514.json,1790753941.114493,1 +v2anneal_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.62793573179996,0.02105160824343241,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b176fe81ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-48.137074.json,1790754288.937839,1 +v2anneal_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7063882323558047,0.0044338567511759495,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b176fe81ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-48.137074.json,1790754288.937839,1 +v2anneal_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2952461608328415,0.007200190494918774,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b176fe81ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-48.137074.json,1790754288.937839,1 +v2anneal_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.36603469849959,0.013968023876800644,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b176fe81ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-48.137074.json,1790754288.937839,1 +v2anneal_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.27680487229327,0.018275602633816567,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/38c804f2fb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-15.848740.json,1790787196.649022,1 +v2anneal_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7106319299227449,0.004036625376460495,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/38c804f2fb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-15.848740.json,1790787196.649022,1 +v2anneal_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28236336434146125,0.006556343274917702,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/38c804f2fb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-15.848740.json,1790787196.649022,1 +v2anneal_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.11906617975623,0.011574616819375789,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/38c804f2fb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-15.848740.json,1790787196.649022,1 +v2anneal_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.391066491334996,0.018852782785640714,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5000354e03/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-18.876533.json,1790754259.737613,1 +v2anneal_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6719679529054059,0.004296638209840715,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5000354e03/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-18.876533.json,1790754259.737613,1 +v2anneal_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2315560147984029,0.006024844726764598,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5000354e03/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-18.876533.json,1790754259.737613,1 +v2anneal_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.65480382415053,0.013508390389602167,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/5000354e03/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-18.876533.json,1790754259.737613,1 +v2anneal_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.92337517529059,0.018563578546152083,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/7934fd127e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.584596.json,1790753809.78707,1 +v2anneal_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6551427593508777,0.004347419808816709,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/7934fd127e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.584596.json,1790753809.78707,1 +v2anneal_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2134005838196058,0.0058940947350989426,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/7934fd127e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.584596.json,1790753809.78707,1 +v2anneal_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.946069190386986,0.013324824019329667,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/7934fd127e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.584596.json,1790753809.78707,1 +v2anneal_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.17256351085131,0.019670356639361557,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/770ed48fea/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-44.711006.json,1790754285.581113,1 +v2anneal_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6549619611091593,0.0043867104243482625,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/770ed48fea/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-44.711006.json,1790754285.581113,1 +v2anneal_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22487096279707122,0.0062599327634735805,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/770ed48fea/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-44.711006.json,1790754285.581113,1 +v2anneal_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.65952335450019,0.013329163741625077,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/770ed48fea/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-44.711006.json,1790754285.581113,1 +v2anneal_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.70858443798538,0.01735818023196172,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e5641b92ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-23.233913.json,1790753964.059432,1 +v2anneal_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6529825419376374,0.003930470033693993,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e5641b92ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-23.233913.json,1790753964.059432,1 +v2anneal_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20208083734511054,0.005439165885939003,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e5641b92ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-23.233913.json,1790753964.059432,1 +v2anneal_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.28168522831689,0.012178337844659281,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e5641b92ef/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-23.233913.json,1790753964.059432,1 +v2anneal_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,21.63253011238874,0.017309103326865607,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/85af07a961/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-18-30.091206.json,1790756310.703851,1 +v2anneal_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5172090645073578,0.0044181804488086915,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/85af07a961/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-18-30.091206.json,1790756310.703851,1 +v2anneal_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.08922988743878141,0.003926348898805715,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/85af07a961/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-18-30.091206.json,1790756310.703851,1 +v2anneal_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,47.76099258182989,0.013364661956292533,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/85af07a961/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-18-30.091206.json,1790756310.703851,1 +v2anneal_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.955862277584835,0.01936428307663298,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e2ea4577e1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-53.432110.json,1790753934.268409,1 +v2anneal_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6415272173858769,0.004524096375448504,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e2ea4577e1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-53.432110.json,1790753934.268409,1 +v2anneal_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20693230471818935,0.006043223982450675,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e2ea4577e1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-53.432110.json,1790753934.268409,1 +v2anneal_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.39515533168688,0.014099394086835849,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e2ea4577e1/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-38-53.432110.json,1790753934.268409,1 +v2anneal_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.14633631433362,0.02006170964535263,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0b28973b54/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-25.576619.json,1790754326.390091,1 +v2anneal_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6717562343595578,0.004412134414647363,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0b28973b54/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-25.576619.json,1790754326.390091,1 +v2anneal_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23384912318470588,0.006397751229584828,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0b28973b54/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-25.576619.json,1790754326.390091,1 +v2anneal_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.69941757019636,0.013870331758271619,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/0b28973b54/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-45-25.576619.json,1790754326.390091,1 +v2anneal_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.43616157099693,0.018664502001151478,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c5a16eaf11/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-46.573663.json,1790753807.430426,1 +v2anneal_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7144934747485994,0.003864228602580939,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c5a16eaf11/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-46.573663.json,1790753807.430426,1 +v2anneal_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2859559242464927,0.00628309998137778,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c5a16eaf11/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-46.573663.json,1790753807.430426,1 +v2anneal_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.09406776782394,0.012419769010781859,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/c5a16eaf11/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-46.573663.json,1790753807.430426,1 +v2anneal_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,58.53836612939456,0.01997464882486986,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b4ba980feb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-52.377525.json,1790753813.337132,1 +v2anneal_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7872098797546123,0.0037840251467578007,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b4ba980feb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-52.377525.json,1790753813.337132,1 +v2anneal_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.4259012221431704,0.0076208396358273655,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b4ba980feb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-52.377525.json,1790753813.337132,1 +v2anneal_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,77.08299423656761,0.012023549948663925,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/b4ba980feb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-52.377525.json,1790753813.337132,1 +v2anneal_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.17473937242232,0.018337327275287713,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3b0b6168c6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-47.815235.json,1790753808.876035,1 +v2anneal_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6193414709192107,0.0043278450263979015,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3b0b6168c6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-47.815235.json,1790753808.876035,1 +v2anneal_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17786653227988966,0.0053029115808458155,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3b0b6168c6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-47.815235.json,1790753808.876035,1 +v2anneal_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.110179132974906,0.013139944364727785,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/3b0b6168c6/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-47.815235.json,1790753808.876035,1 +v2anneal_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.349104803521925,0.019042909231896915,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/70f0c7e40a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.593362.json,1790754273.459884,1 +v2anneal_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7066995473671138,0.003913616363495782,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/70f0c7e40a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.593362.json,1790754273.459884,1 +v2anneal_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28830613821384016,0.0063257109752187235,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/70f0c7e40a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.593362.json,1790754273.459884,1 +v2anneal_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.73913800805703,0.012457942992051394,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/70f0c7e40a/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.593362.json,1790754273.459884,1 +v2anneal_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.21869532030526,0.0175252982576263,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/ec80d80200/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-20.084321.json,1790787200.9536,1 +v2anneal_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6187592391521614,0.004213656299728107,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/ec80d80200/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-20.084321.json,1790787200.9536,1 +v2anneal_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16995904516366717,0.005063041263274251,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/ec80d80200/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-20.084321.json,1790787200.9536,1 +v2anneal_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.29114647402319,0.012577953659595478,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/ec80d80200/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T16-53-20.084321.json,1790787200.9536,1 +v2anneal_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,52.00089721650374,0.019399392702108224,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/00ea46eb0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-10.345941.json,1790755931.208219,1 +v2anneal_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7524614877953264,0.003988664429173594,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/00ea46eb0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-10.345941.json,1790755931.208219,1 +v2anneal_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.35354027067683375,0.007157678913034543,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/00ea46eb0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-10.345941.json,1790755931.208219,1 +v2anneal_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.3076890531731,0.013002092492689734,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/00ea46eb0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T08-12-10.345941.json,1790755931.208219,1 +v2anneal_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.415448183003896,0.019662488850688956,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e79fc27b90/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-13.318153.json,1790753954.177926,1 +v2anneal_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7183554478197022,0.004097515757901205,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e79fc27b90/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-13.318153.json,1790753954.177926,1 +v2anneal_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2948686121058862,0.006672858842154563,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e79fc27b90/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-13.318153.json,1790753954.177926,1 +v2anneal_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.85905872630244,0.012809926967357348,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e79fc27b90/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-39-13.318153.json,1790753954.177926,1 +v2anneal_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,42.466944407812726,0.020187081169940307,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/9d3106478f/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.359152.json,1790754273.151954,1 +v2anneal_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6871946715569748,0.004341919330422303,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/9d3106478f/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.359152.json,1790754273.151954,1 +v2anneal_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.25361003896952355,0.00662926336834648,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/9d3106478f/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.359152.json,1790754273.151954,1 +v2anneal_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.727902794223,0.013246147333933095,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/9d3106478f/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-32.359152.json,1790754273.151954,1 +v2anneal_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.93461567643493,0.01858152274925595,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71cb1ce53b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-35.137126.json,1790753795.979147,1 +v2anneal_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6633840609848662,0.004160689602858843,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71cb1ce53b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-35.137126.json,1790753795.979147,1 +v2anneal_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2208823740130061,0.005847959377797158,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71cb1ce53b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-35.137126.json,1790753795.979147,1 +v2anneal_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.50392791957384,0.012887467585880915,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/71cb1ce53b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-35.137126.json,1790753795.979147,1 +v2anneal_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.23816885212473,0.020107078397231862,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2853a3f529/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-29.880964.json,1790754030.703189,1 +v2anneal_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6304025758975572,0.00403919699369454,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2853a3f529/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-29.880964.json,1790754030.703189,1 +v2anneal_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17734774212435073,0.005154646229857466,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2853a3f529/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-29.880964.json,1790754030.703189,1 +v2anneal_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.94323414950996,0.012481021207891081,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/2853a3f529/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-40-29.880964.json,1790754030.703189,1 +v2anneal_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.72656745997428,0.018729165013152037,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/528c74883b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-50.378710.json,1790753811.172747,1 +v2anneal_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7195120437941914,0.003979877050855355,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/528c74883b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-50.378710.json,1790753811.172747,1 +v2anneal_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2968650587735023,0.006527073797296061,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/528c74883b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-50.378710.json,1790753811.172747,1 +v2anneal_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.81378353396836,0.012176049238225501,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/528c74883b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-50.378710.json,1790753811.172747,1 +v2anneal_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,51.18553784123636,0.01893545572462668,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/054294ab0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.528825.json,1790753809.373516,1 +v2anneal_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7435431882688878,0.0038234365027966155,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/054294ab0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.528825.json,1790753809.373516,1 +v2anneal_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3373195296045636,0.006868678808483843,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/054294ab0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.528825.json,1790753809.373516,1 +v2anneal_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,71.11038887260742,0.012458973744682682,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/054294ab0b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-36-48.528825.json,1790753809.373516,1 +v2anneal_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.39504446568901,0.01916167862275869,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e1f506c2f7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-46.808392.json,1790754287.653603,1 +v2anneal_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6747213409005948,0.004259018784201489,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e1f506c2f7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-46.808392.json,1790754287.653603,1 +v2anneal_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2376778277724055,0.006369364686400821,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e1f506c2f7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-46.808392.json,1790754287.653603,1 +v2anneal_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.52640030426099,0.013556580797381404,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e1f506c2f7/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-46.808392.json,1790754287.653603,1 +v2anneal_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.00412025410181,0.01879270580214464,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/eb217d5a5e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-37.715744.json,1790754278.530243,1 +v2anneal_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6926183355255301,0.004151670938866643,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/eb217d5a5e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-37.715744.json,1790754278.530243,1 +v2anneal_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.25807757180096513,0.006350528828525068,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/eb217d5a5e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-37.715744.json,1790754278.530243,1 +v2anneal_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.61785547888566,0.012943099097793665,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/eb217d5a5e/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-44-37.715744.json,1790754278.530243,1 +v2anneal_120k,global_mgsm_ca,5,lm-eval,vllm,,exact_match,flexible-extract,0.38,0.030760116042626028,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_cs,5,lm-eval,vllm,,exact_match,flexible-extract,0.34,0.030020073605457907,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.344,0.03010450339231639,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_el,5,lm-eval,vllm,,exact_match,flexible-extract,0.356,0.03034368065715322,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.344,0.03010450339231639,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.372,0.03063032594455832,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_eu,5,lm-eval,vllm,,exact_match,flexible-extract,0.292,0.028814320402205648,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.328,0.029752391824475387,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_gl,5,lm-eval,vllm,,exact_match,flexible-extract,0.352,0.030266288057359945,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_hu,5,lm-eval,vllm,,exact_match,flexible-extract,0.284,0.028576958730437405,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mgsm_sr,5,lm-eval,vllm,,exact_match,flexible-extract,0.348,0.030186568464511704,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T22-40-52.600731.json,1790807797.3362224,1 +v2anneal_120k,global_mmlu_full_cs,5,lm-eval,vllm,yes,acc,none,0.6697051702036747,0.003752870796175007,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_abstract_algebra,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_anatomy,5,lm-eval,vllm,,acc,none,0.5777777777777777,0.042667634040995855,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_astronomy,5,lm-eval,vllm,,acc,none,0.7697368421052632,0.03426059424403165,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7245283018867924,0.027495663683724022,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_college_biology,5,lm-eval,vllm,,acc,none,0.8263888888888888,0.03167473383795719,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7531914893617021,0.02818544130123409,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6620689655172414,0.03941707632064884,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6534391534391535,0.024508777521028414,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_formal_logic,5,lm-eval,vllm,,acc,none,0.5952380952380952,0.043902592653775656,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_biology,5,lm-eval,vllm,,acc,none,0.8161290322580645,0.022037217340267787,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_geography,5,lm-eval,vllm,,acc,none,0.8282828282828283,0.02686971618742987,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7384615384615385,0.0222821412042044,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4444444444444444,0.030296771286067326,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7857142857142857,0.026653531596715505,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8678899082568807,0.014517801914598314,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.031919234456861886,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8607594936708861,0.022535526352692684,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_human_aging,5,lm-eval,vllm,,acc,none,0.7399103139013453,0.029442495585857424,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_human_sexuality,5,lm-eval,vllm,,acc,none,0.8244274809160306,0.03336820338476075,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_humanities,5,lm-eval,vllm,yes,acc,none,0.5980871413390011,0.006662487628381383,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7423312883435583,0.03436150827846915,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_machine_learning,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_marketing,5,lm-eval,vllm,,acc,none,0.8504273504273504,0.023365051491753757,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_miscellaneous,5,lm-eval,vllm,,acc,none,0.7816091954022989,0.014774358319934516,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_moral_disputes,5,lm-eval,vllm,,acc,none,0.708092485549133,0.02447699407624737,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_moral_scenarios,5,lm-eval,vllm,,acc,none,0.33519553072625696,0.015788007190185846,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_nutrition,5,lm-eval,vllm,,acc,none,0.7581699346405228,0.024518195641879306,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_other,5,lm-eval,vllm,yes,acc,none,0.6977792082394593,0.007947565658089746,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_prehistory,5,lm-eval,vllm,,acc,none,0.7808641975308642,0.02301670564026216,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_professional_accounting,5,lm-eval,vllm,,acc,none,0.44680851063829785,0.02965823509766695,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_professional_law,5,lm-eval,vllm,,acc,none,0.5013037809647979,0.012770192691057138,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_professional_medicine,5,lm-eval,vllm,,acc,none,0.6911764705882353,0.028064998167040053,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_professional_psychology,5,lm-eval,vllm,,acc,none,0.6977124183006536,0.018579232711113967,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_security_studies,5,lm-eval,vllm,,acc,none,0.7673469387755102,0.02704925791589615,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7773805654858629,0.007335920570851386,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_stem,5,lm-eval,vllm,yes,acc,none,0.6438312718046305,0.008241246303279116,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_cs_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c3da106bfc_2026-09-30T08-17-59.542493.json,1790755924.982503,1 +v2anneal_120k,global_mmlu_full_de,5,lm-eval,vllm,yes,acc,none,0.6719128329297821,0.003756987827625916,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_abstract_algebra,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_anatomy,5,lm-eval,vllm,,acc,none,0.5777777777777777,0.042667634040995855,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_business_ethics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.720754716981132,0.027611163402399694,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_college_biology,5,lm-eval,vllm,,acc,none,0.7708333333333334,0.03514697467862389,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_college_chemistry,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_college_computer_science,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_college_medicine,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.03435568056047877,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7319148936170212,0.028957342788342354,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_econometrics,5,lm-eval,vllm,,acc,none,0.5526315789473685,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6413793103448275,0.03996629574876715,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6084656084656085,0.025138091388851137,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_formal_logic,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.043435254289490965,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_biology,5,lm-eval,vllm,,acc,none,0.8258064516129032,0.02157624818451461,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6305418719211823,0.03395970381998578,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9222797927461139,0.01932180555722318,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7410256410256411,0.02221110681006163,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8277310924369747,0.024528664971305403,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_physics,5,lm-eval,vllm,,acc,none,0.5298013245033113,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8532110091743119,0.015173141845126333,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6481481481481481,0.032568505702936484,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8185654008438819,0.025085961144579647,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_human_aging,5,lm-eval,vllm,,acc,none,0.672645739910314,0.0314938467099413,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_human_sexuality,5,lm-eval,vllm,,acc,none,0.816793893129771,0.03392770926494735,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_humanities,5,lm-eval,vllm,yes,acc,none,0.6004250797024442,0.006680709954633325,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_international_law,5,lm-eval,vllm,,acc,none,0.7768595041322314,0.038007544752287334,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_jurisprudence,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.04414343666854928,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_marketing,5,lm-eval,vllm,,acc,none,0.8846153846153846,0.0209301931851793,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_miscellaneous,5,lm-eval,vllm,,acc,none,0.7905491698595147,0.014551310568143733,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3541899441340782,0.015995644947299357,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_nutrition,5,lm-eval,vllm,,acc,none,0.7450980392156863,0.024954184324879967,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_other,5,lm-eval,vllm,yes,acc,none,0.7048599935629224,0.007905274748860942,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_philosophy,5,lm-eval,vllm,,acc,none,0.7459807073954984,0.024723861504771655,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_prehistory,5,lm-eval,vllm,,acc,none,0.7932098765432098,0.022535006705942877,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_professional_accounting,5,lm-eval,vllm,,acc,none,0.4787234042553192,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_professional_law,5,lm-eval,vllm,,acc,none,0.49282920469361147,0.012768922739553434,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_professional_medicine,5,lm-eval,vllm,,acc,none,0.6801470588235294,0.028332959514031246,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_professional_psychology,5,lm-eval,vllm,,acc,none,0.704248366013072,0.01846315413263271,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_security_studies,5,lm-eval,vllm,,acc,none,0.7306122448979592,0.028401252029022956,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7812804679883003,0.007312855340974806,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_sociology,5,lm-eval,vllm,,acc,none,0.845771144278607,0.025538433368578303,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_stem,5,lm-eval,vllm,yes,acc,none,0.6393910561370124,0.008304461499253036,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_virology,5,lm-eval,vllm,,acc,none,0.5301204819277109,0.03885425420866771,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_de_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bb73671392_2026-09-30T07-43-33.342877.json,1790753866.0251822,1 +v2anneal_120k,global_mmlu_full_el,5,lm-eval,vllm,yes,acc,none,0.6526135878080046,0.0038343385914138793,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_abstract_algebra,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_astronomy,5,lm-eval,vllm,,acc,none,0.756578947368421,0.03492349668884235,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_business_ethics,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_college_biology,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.0389907368735733,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_college_medicine,5,lm-eval,vllm,,acc,none,0.6994219653179191,0.03496101481191176,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7361702127659574,0.028809989854102946,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6243386243386243,0.02494236893115981,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_formal_logic,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.044444444444444446,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_global_facts,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_biology,5,lm-eval,vllm,,acc,none,0.8161290322580645,0.022037217340267787,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.034139638059062394,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_geography,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.02747960301053882,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7538461538461538,0.02184086699042312,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.42592592592592593,0.0301491356013659,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8067226890756303,0.02564947026588922,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_physics,5,lm-eval,vllm,,acc,none,0.543046357615894,0.0406732517424744,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8036697247706422,0.017030719339154426,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.031919234456861886,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.02675640153807894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_human_aging,5,lm-eval,vllm,,acc,none,0.7085201793721974,0.03050028317654591,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_humanities,5,lm-eval,vllm,yes,acc,none,0.5895855472901169,0.006749299116578611,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_jurisprudence,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.040774947092526284,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_machine_learning,5,lm-eval,vllm,,acc,none,0.5446428571428571,0.04726835553719097,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_marketing,5,lm-eval,vllm,,acc,none,0.8418803418803419,0.02390232554956044,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_medical_genetics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_miscellaneous,5,lm-eval,vllm,,acc,none,0.7100893997445722,0.016225017944770968,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_moral_disputes,5,lm-eval,vllm,,acc,none,0.7254335260115607,0.02402774515526503,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_moral_scenarios,5,lm-eval,vllm,,acc,none,0.358659217877095,0.016040454426164447,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_nutrition,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.025646863097137932,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_other,5,lm-eval,vllm,yes,acc,none,0.6610878661087866,0.008243426337481107,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_prehistory,5,lm-eval,vllm,,acc,none,0.7160493827160493,0.02508947852376511,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_professional_accounting,5,lm-eval,vllm,,acc,none,0.4326241134751773,0.029555454236778834,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_professional_law,5,lm-eval,vllm,,acc,none,0.4863102998696219,0.012765448722610156,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_professional_medicine,5,lm-eval,vllm,,acc,none,0.6286764705882353,0.029349803139765818,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_professional_psychology,5,lm-eval,vllm,,acc,none,0.6911764705882353,0.01869085027359537,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_public_relations,5,lm-eval,vllm,,acc,none,0.6727272727272727,0.04494290866252085,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7647058823529411,0.007528408892687631,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_sociology,5,lm-eval,vllm,,acc,none,0.8308457711442786,0.026508590656233278,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_stem,5,lm-eval,vllm,yes,acc,none,0.6289248334919124,0.008379142404051347,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_virology,5,lm-eval,vllm,,acc,none,0.46987951807228917,0.038854254208667706,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_el_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4d5de4c8b7_2026-09-30T07-44-18.677187.json,1790753864.4299192,1 +v2anneal_120k,global_mmlu_full_en,5,lm-eval,vllm,yes,acc,none,0.72746047571571,0.003597219764774364,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_abstract_algebra,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_anatomy,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.0417165416135454,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_business_ethics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7584905660377359,0.02634148037111831,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_college_biology,5,lm-eval,vllm,,acc,none,0.8611111111111112,0.028919802956134912,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_college_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_college_mathematics,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_computer_security,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7957446808510639,0.02635515841334947,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_econometrics,5,lm-eval,vllm,,acc,none,0.6140350877192983,0.04579639422070431,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7379310344827587,0.03664666337225255,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6402116402116402,0.024718075944129204,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_formal_logic,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.042639068927951274,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_global_facts,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_biology,5,lm-eval,vllm,,acc,none,0.8741935483870967,0.018865834288030025,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6798029556650246,0.032826493853041455,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.027998073798781685,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_geography,5,lm-eval,vllm,,acc,none,0.8939393939393939,0.02193804773885311,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9585492227979274,0.01438543285747641,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.782051282051282,0.020932445774463234,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5148148148148148,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8823529411764706,0.020928472557788826,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_physics,5,lm-eval,vllm,,acc,none,0.5695364238410596,0.04042809961395634,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_psychology,5,lm-eval,vllm,,acc,none,0.9137614678899083,0.012035597300116307,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.03167468706828983,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8725490196078431,0.02340553048084634,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8818565400843882,0.021011052659878477,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_human_aging,5,lm-eval,vllm,,acc,none,0.7802690582959642,0.027790177064383567,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_human_sexuality,5,lm-eval,vllm,,acc,none,0.8473282442748091,0.031545216720054704,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_humanities,5,lm-eval,vllm,yes,acc,none,0.6820403825717322,0.006506514984965544,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_jurisprudence,5,lm-eval,vllm,,acc,none,0.8240740740740741,0.036809181416738786,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7914110429447853,0.03192193448934723,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_machine_learning,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.045479609997643805,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_marketing,5,lm-eval,vllm,,acc,none,0.8931623931623932,0.02023714900899092,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_miscellaneous,5,lm-eval,vllm,,acc,none,0.8250319284802043,0.01358661921990341,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_moral_disputes,5,lm-eval,vllm,,acc,none,0.8005780346820809,0.02151190065425248,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5363128491620112,0.01667834189453305,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_nutrition,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.02428861946604616,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_other,5,lm-eval,vllm,yes,acc,none,0.7415513356935951,0.007613923104461062,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_philosophy,5,lm-eval,vllm,,acc,none,0.7620578778135049,0.02418515064781868,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_prehistory,5,lm-eval,vllm,,acc,none,0.8395061728395061,0.02042395535477805,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_professional_accounting,5,lm-eval,vllm,,acc,none,0.5319148936170213,0.02976667507587383,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_professional_law,5,lm-eval,vllm,,acc,none,0.5691003911342895,0.01264769588954738,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_professional_medicine,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.026799562024887664,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_professional_psychology,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.017555818091322294,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_public_relations,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.04350271442923247,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_security_studies,5,lm-eval,vllm,,acc,none,0.7795918367346939,0.026537045312145312,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8280792980175495,0.006643628608638319,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_sociology,5,lm-eval,vllm,,acc,none,0.8805970149253731,0.022928793277219726,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_stem,5,lm-eval,vllm,yes,acc,none,0.6831588962892483,0.008003661378727453,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_virology,5,lm-eval,vllm,,acc,none,0.5481927710843374,0.0387437155658795,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_en_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/94de97d5ce_2026-09-30T08-34-13.259306.json,1790756928.94976,1 +v2anneal_120k,global_mmlu_full_es,5,lm-eval,vllm,yes,acc,none,0.6874376869391825,0.003728818484984839,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_anatomy,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.04292596718256977,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7056603773584905,0.028049186315695293,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_college_biology,5,lm-eval,vllm,,acc,none,0.8194444444444444,0.03216600808802272,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_college_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_college_physics,5,lm-eval,vllm,,acc,none,0.49019607843137253,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_computer_security,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7489361702127659,0.02834696377716252,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_econometrics,5,lm-eval,vllm,,acc,none,0.6228070175438597,0.0455952214195822,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6375661375661376,0.024757473902752066,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_formal_logic,5,lm-eval,vllm,,acc,none,0.626984126984127,0.043255060420170875,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_global_facts,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_biology,5,lm-eval,vllm,,acc,none,0.8483870967741935,0.020402616654416734,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6748768472906403,0.03295797566311267,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_geography,5,lm-eval,vllm,,acc,none,0.8434343434343434,0.025890520358141458,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8756476683937824,0.02381447708659357,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7871794871794872,0.020752423722128037,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48148148148148145,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8361344537815126,0.024044054940440488,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_physics,5,lm-eval,vllm,,acc,none,0.543046357615894,0.0406732517424744,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8715596330275229,0.014344977542914248,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8607594936708861,0.022535526352692684,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_human_aging,5,lm-eval,vllm,,acc,none,0.7219730941704036,0.030069584874494053,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_humanities,5,lm-eval,vllm,yes,acc,none,0.620403825717322,0.006686733429319939,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_jurisprudence,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.04414343666854928,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_machine_learning,5,lm-eval,vllm,,acc,none,0.5625,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_marketing,5,lm-eval,vllm,,acc,none,0.8717948717948718,0.021901905115073377,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_miscellaneous,5,lm-eval,vllm,,acc,none,0.7982120051085568,0.014351702181636911,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_moral_disputes,5,lm-eval,vllm,,acc,none,0.7601156069364162,0.02298959254312351,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_moral_scenarios,5,lm-eval,vllm,,acc,none,0.423463687150838,0.016525425898773562,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_nutrition,5,lm-eval,vllm,,acc,none,0.7287581699346405,0.025457756696667815,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_other,5,lm-eval,vllm,yes,acc,none,0.7064692629546186,0.007937951875125856,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_philosophy,5,lm-eval,vllm,,acc,none,0.7491961414790996,0.024619771956697113,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_prehistory,5,lm-eval,vllm,,acc,none,0.7654320987654321,0.0235768817440057,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_professional_accounting,5,lm-eval,vllm,,acc,none,0.5212765957446809,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_professional_law,5,lm-eval,vllm,,acc,none,0.500651890482399,0.012770225252255563,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_professional_medicine,5,lm-eval,vllm,,acc,none,0.6838235294117647,0.028245687391462857,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_professional_psychology,5,lm-eval,vllm,,acc,none,0.7369281045751634,0.01781267654232072,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8007799805004875,0.007119363215298641,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_stem,5,lm-eval,vllm,yes,acc,none,0.6581033935934031,0.008170378681286278,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_virology,5,lm-eval,vllm,,acc,none,0.5240963855421686,0.03887971849597267,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_es_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e9e468008e_2026-09-30T08-19-53.999481.json,1790756046.3879473,1 +v2anneal_120k,global_mmlu_full_fr,5,lm-eval,vllm,yes,acc,none,0.6817404928072924,0.003730267366728688,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_anatomy,5,lm-eval,vllm,,acc,none,0.5851851851851851,0.04256193767901412,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7622641509433963,0.026199808807561956,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_college_physics,5,lm-eval,vllm,,acc,none,0.45098039215686275,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7659574468085106,0.02767845257821238,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_econometrics,5,lm-eval,vllm,,acc,none,0.5701754385964912,0.04657047260594963,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.024796060602699895,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_global_facts,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.625615763546798,0.03405155380561957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8131313131313131,0.02777253333421894,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.735897435897436,0.02235219373745328,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4962962962962963,0.030484701665084435,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7983193277310925,0.026064313406304485,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5827814569536424,0.040261414976346124,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8440366972477065,0.015555802713590066,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03214952147802747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.024857478080250486,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8734177215189873,0.021644195727955198,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_human_aging,5,lm-eval,vllm,,acc,none,0.7174887892376681,0.030216831011508755,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_human_sexuality,5,lm-eval,vllm,,acc,none,0.816793893129771,0.03392770926494735,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_humanities,5,lm-eval,vllm,yes,acc,none,0.6153028692879915,0.006589471865302478,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_international_law,5,lm-eval,vllm,,acc,none,0.8677685950413223,0.030922788320445795,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.04019107472557348,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7177914110429447,0.03536117886664741,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_marketing,5,lm-eval,vllm,,acc,none,0.8717948717948718,0.021901905115073377,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_miscellaneous,5,lm-eval,vllm,,acc,none,0.8058748403575989,0.014143970276657597,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7745664739884393,0.02249723019096748,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.35083798882681566,0.0159610366752309,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_nutrition,5,lm-eval,vllm,,acc,none,0.7450980392156863,0.024954184324879967,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_other,5,lm-eval,vllm,yes,acc,none,0.7196652719665272,0.007801703442256751,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_prehistory,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.02277971908873342,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_professional_accounting,5,lm-eval,vllm,,acc,none,0.5035460992907801,0.029826749153280853,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_professional_law,5,lm-eval,vllm,,acc,none,0.5143415906127771,0.012764981829524309,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_professional_medicine,5,lm-eval,vllm,,acc,none,0.7169117647058824,0.027365861131513815,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.01863559403442406,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7747806304842378,0.007423231266373894,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_stem,5,lm-eval,vllm,yes,acc,none,0.6527117031398668,0.00822941700385638,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_fr_world_religions,5,lm-eval,vllm,,acc,none,0.8304093567251462,0.02878210810540169,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed55a1708c_2026-09-30T08-20-10.085283.json,1790756044.9872532,1 +v2anneal_120k,global_mmlu_full_it,5,lm-eval,vllm,yes,acc,none,0.682025352513887,0.0037583299201274737,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_abstract_algebra,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_astronomy,5,lm-eval,vllm,,acc,none,0.7828947368421053,0.03355045304882924,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7169811320754716,0.027724236492700883,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_college_computer_science,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_college_medicine,5,lm-eval,vllm,,acc,none,0.6820809248554913,0.0355068398916558,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_college_physics,5,lm-eval,vllm,,acc,none,0.5686274509803921,0.049280995972875316,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7787234042553192,0.027136349602424097,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7034482758620689,0.03806142687309988,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.024552292209342713,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_biology,5,lm-eval,vllm,,acc,none,0.8516129032258064,0.02022273755433042,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7818181818181819,0.032250781083062896,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_geography,5,lm-eval,vllm,,acc,none,0.8585858585858586,0.024825909793343353,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9119170984455959,0.020453746601601056,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7461538461538462,0.022066054378726312,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4777777777777778,0.030455413985678415,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8109243697478992,0.025435119438105305,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8642201834862385,0.014686907556339952,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6712962962962963,0.03203614084670054,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8227848101265823,0.024856364184503203,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_human_aging,5,lm-eval,vllm,,acc,none,0.6905829596412556,0.031024411740572237,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_humanities,5,lm-eval,vllm,yes,acc,none,0.6195536663124336,0.006723637844478757,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_logical_fallacies,5,lm-eval,vllm,,acc,none,0.754601226993865,0.033809398139433525,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_machine_learning,5,lm-eval,vllm,,acc,none,0.5892857142857143,0.04669510663875191,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_miscellaneous,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.014866821664709668,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_moral_scenarios,5,lm-eval,vllm,,acc,none,0.42681564245810055,0.01654240195463199,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_nutrition,5,lm-eval,vllm,,acc,none,0.7287581699346405,0.025457756696667815,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_other,5,lm-eval,vllm,yes,acc,none,0.6926295461860316,0.008023291631135028,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_philosophy,5,lm-eval,vllm,,acc,none,0.729903536977492,0.02521804037341055,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_prehistory,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.02346842983245111,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_professional_accounting,5,lm-eval,vllm,,acc,none,0.4645390070921986,0.029752389657427127,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_professional_law,5,lm-eval,vllm,,acc,none,0.5058670143415906,0.012769356925216389,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_professional_medicine,5,lm-eval,vllm,,acc,none,0.6727941176470589,0.028501452860396626,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_professional_psychology,5,lm-eval,vllm,,acc,none,0.7124183006535948,0.018311653053648198,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_security_studies,5,lm-eval,vllm,,acc,none,0.7387755102040816,0.028123429335142832,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7855053623659408,0.007261510331206792,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_sociology,5,lm-eval,vllm,,acc,none,0.8507462686567164,0.02519692987482706,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_stem,5,lm-eval,vllm,yes,acc,none,0.6638122423089121,0.008170950843446854,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_it_world_religions,5,lm-eval,vllm,,acc,none,0.8304093567251462,0.02878210810540169,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a1069d90ee_2026-09-30T08-39-23.628389.json,1790757136.6308763,1 +v2anneal_120k,global_mmlu_full_lt,5,lm-eval,vllm,yes,acc,none,0.6447087309500071,0.003834954661258017,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_anatomy,5,lm-eval,vllm,,acc,none,0.5481481481481482,0.04299268905480864,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_business_ethics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6830188679245283,0.02863723563980094,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_college_biology,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.037455547914624555,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_college_computer_science,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_college_medicine,5,lm-eval,vllm,,acc,none,0.653179190751445,0.03629146670159661,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.723404255319149,0.0292418838696288,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6344827586206897,0.04013124195424389,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.02487081525105711,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_formal_logic,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04426266681379905,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8193548387096774,0.021886178567172513,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6108374384236454,0.03430462416103873,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7696969696969697,0.03287666758603482,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026552207828215258,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6846153846153846,0.023559646983189894,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.42592592592592593,0.0301491356013659,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.027553614467863825,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_physics,5,lm-eval,vllm,,acc,none,0.5364238410596026,0.04071636065944211,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8385321100917431,0.01577623925616323,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7941176470588235,0.028379449451588684,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_human_aging,5,lm-eval,vllm,,acc,none,0.695067264573991,0.03089861088247754,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_humanities,5,lm-eval,vllm,yes,acc,none,0.5706695005313497,0.006727393801655137,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6441717791411042,0.03761521380046734,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7254150702426565,0.015959829933084018,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.02454761779480379,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.30726256983240224,0.015430158846469541,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_nutrition,5,lm-eval,vllm,,acc,none,0.696078431372549,0.026336613469046647,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_other,5,lm-eval,vllm,yes,acc,none,0.6655938204055359,0.008253937102695764,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_prehistory,5,lm-eval,vllm,,acc,none,0.7376543209876543,0.024477222856135194,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_professional_accounting,5,lm-eval,vllm,,acc,none,0.4397163120567376,0.029609912075594054,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_professional_law,5,lm-eval,vllm,,acc,none,0.4706649282920469,0.012748238397365576,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6801470588235294,0.028332959514031246,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_professional_psychology,5,lm-eval,vllm,,acc,none,0.6699346405228758,0.019023726160724508,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7539811504712383,0.00760907636224509,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_stem,5,lm-eval,vllm,yes,acc,none,0.6279733587059942,0.008344418627947905,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_virology,5,lm-eval,vllm,,acc,none,0.5240963855421686,0.03887971849597267,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_lt_world_religions,5,lm-eval,vllm,,acc,none,0.8011695906432749,0.030611116557432514,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95578516c1_2026-09-30T08-52-09.645064.json,1790757990.933255,1 +v2anneal_120k,global_mmlu_full_nl,5,lm-eval,vllm,yes,acc,none,0.6798176897877796,0.0037771316110996704,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_college_biology,5,lm-eval,vllm,,acc,none,0.8263888888888888,0.03167473383795719,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_college_mathematics,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_college_medicine,5,lm-eval,vllm,,acc,none,0.6820809248554913,0.0355068398916558,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7489361702127659,0.02834696377716252,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6534391534391535,0.024508777521028414,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8387096774193549,0.020923327006423326,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6157635467980296,0.03422398565657553,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8383838383838383,0.02622591986362927,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9222797927461139,0.01932180555722318,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7564102564102564,0.021763733684173926,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4740740740740741,0.030444528528810785,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8678899082568807,0.014517801914598314,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.7037037037037037,0.03114144782353603,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.024857478080250486,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_human_aging,5,lm-eval,vllm,,acc,none,0.726457399103139,0.029918586707798872,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_human_sexuality,5,lm-eval,vllm,,acc,none,0.8244274809160306,0.03336820338476075,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_humanities,5,lm-eval,vllm,yes,acc,none,0.6242295430393199,0.006743691932231002,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_jurisprudence,5,lm-eval,vllm,,acc,none,0.8055555555555556,0.038260763248848646,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7300613496932515,0.034878251684978955,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_machine_learning,5,lm-eval,vllm,,acc,none,0.6160714285714286,0.04616143075028549,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_medical_genetics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7624521072796935,0.015218733046150228,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.024257901705323326,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.48156424581005586,0.016711130497782726,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_other,5,lm-eval,vllm,yes,acc,none,0.6874798841326037,0.008072337219895169,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_philosophy,5,lm-eval,vllm,,acc,none,0.7363344051446945,0.02502553850053229,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_prehistory,5,lm-eval,vllm,,acc,none,0.7716049382716049,0.02335821184062624,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_professional_accounting,5,lm-eval,vllm,,acc,none,0.45390070921985815,0.029700453247291494,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_professional_law,5,lm-eval,vllm,,acc,none,0.49478487614080835,0.012769541449652715,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6507352941176471,0.02895975519682485,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.01863559403442406,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_security_studies,5,lm-eval,vllm,,acc,none,0.7591836734693878,0.027372942201788125,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7819304517387066,0.007296650035422438,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_stem,5,lm-eval,vllm,yes,acc,none,0.6555661274976213,0.008229245464897578,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_virology,5,lm-eval,vllm,,acc,none,0.536144578313253,0.038823108508905954,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_nl_world_religions,5,lm-eval,vllm,,acc,none,0.7953216374269005,0.03094445977853322,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417cbe8115_2026-09-30T08-35-59.063169.json,1790757007.0132554,1 +v2anneal_120k,global_mmlu_full_pl,5,lm-eval,vllm,yes,acc,none,0.6667141432844325,0.003799249241086684,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_anatomy,5,lm-eval,vllm,,acc,none,0.5259259259259259,0.043135316967505756,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_astronomy,5,lm-eval,vllm,,acc,none,0.75,0.03523807393012047,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_college_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7148936170212766,0.029513196625539355,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_econometrics,5,lm-eval,vllm,,acc,none,0.5175438596491229,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7034482758620689,0.03806142687309988,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.02467786284133279,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_global_facts,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8161290322580645,0.022037217340267787,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6502463054187192,0.033554009049695604,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.030117688929503603,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.02747960301053882,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7487179487179487,0.021992016662370557,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45185185185185184,0.030343862998512657,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7815126050420168,0.026841514322958934,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8550458715596331,0.015094215699700396,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6712962962962963,0.03203614084670054,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8578431372549019,0.024509803921568627,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8438818565400844,0.02362715946031866,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_human_aging,5,lm-eval,vllm,,acc,none,0.6816143497757847,0.03126580522513711,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_humanities,5,lm-eval,vllm,yes,acc,none,0.6091392136025505,0.006722798551955746,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7407407407407407,0.04236511258094632,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7055214723926381,0.03581165790474083,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_machine_learning,5,lm-eval,vllm,,acc,none,0.5089285714285714,0.04745033255489126,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_marketing,5,lm-eval,vllm,,acc,none,0.8632478632478633,0.022509033937077844,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_medical_genetics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7522349936143039,0.01543808308056889,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7254335260115607,0.02402774515526503,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.41675977653631285,0.016489134962438902,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_nutrition,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.025261691219729484,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_other,5,lm-eval,vllm,yes,acc,none,0.6800772449308015,0.00810505359029553,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_philosophy,5,lm-eval,vllm,,acc,none,0.7170418006430869,0.025583062489984907,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_prehistory,5,lm-eval,vllm,,acc,none,0.7438271604938271,0.02428853363772609,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_professional_accounting,5,lm-eval,vllm,,acc,none,0.41134751773049644,0.02935491115994096,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_professional_law,5,lm-eval,vllm,,acc,none,0.4869621903520209,0.01276589388383549,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6727941176470589,0.028501452860396626,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6813725490196079,0.018850084696468674,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_security_studies,5,lm-eval,vllm,,acc,none,0.8204081632653061,0.024573293589585647,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7731556711082223,0.007412902985589852,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_stem,5,lm-eval,vllm,yes,acc,none,0.6355851569933397,0.008338602379348973,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pl_world_religions,5,lm-eval,vllm,,acc,none,0.847953216374269,0.027539122889061483,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fa85104ae_2026-09-30T07-37-44.955154.json,1790753514.0098088,1 +v2anneal_120k,global_mmlu_full_pt,5,lm-eval,vllm,yes,acc,none,0.682025352513887,0.0037448204298812723,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7396226415094339,0.027008766090708045,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_college_biology,5,lm-eval,vllm,,acc,none,0.7986111111111112,0.033536474697138365,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_college_chemistry,5,lm-eval,vllm,,acc,none,0.55,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_computer_security,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7446808510638298,0.0285048564705142,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6137566137566137,0.02507598176760173,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_formal_logic,5,lm-eval,vllm,,acc,none,0.626984126984127,0.043255060420170875,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8354838709677419,0.021090847745939306,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6650246305418719,0.03320852742348313,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8434343434343434,0.025890520358141458,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9119170984455959,0.020453746601601056,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7384615384615385,0.0222821412042044,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45555555555555555,0.03036486250482447,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7899159663865546,0.026461398717471864,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_physics,5,lm-eval,vllm,,acc,none,0.543046357615894,0.0406732517424744,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8715596330275229,0.014344977542914248,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6620370370370371,0.03225941352631297,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8480392156862745,0.025195658428931827,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8312236286919831,0.02438140683258622,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7862595419847328,0.03595461611774691,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_humanities,5,lm-eval,vllm,yes,acc,none,0.6172157279489905,0.0066998555277832175,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_jurisprudence,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.038935425188248496,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7361963190184049,0.03462419931615622,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_machine_learning,5,lm-eval,vllm,,acc,none,0.5625,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_management,5,lm-eval,vllm,,acc,none,0.8349514563106796,0.03675668832233187,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7867177522349936,0.014648172749593532,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.41899441340782123,0.016501579306861677,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_nutrition,5,lm-eval,vllm,,acc,none,0.7418300653594772,0.025058503316958167,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_other,5,lm-eval,vllm,yes,acc,none,0.7064692629546186,0.007917212960405633,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_prehistory,5,lm-eval,vllm,,acc,none,0.7654320987654321,0.0235768817440057,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_professional_accounting,5,lm-eval,vllm,,acc,none,0.4716312056737589,0.029779450957303062,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_professional_law,5,lm-eval,vllm,,acc,none,0.4980443285528031,0.012770138422208597,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_professional_medicine,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.027678468642144703,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_professional_psychology,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.01791797406959478,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_public_relations,5,lm-eval,vllm,,acc,none,0.7,0.04389311454644288,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_security_studies,5,lm-eval,vllm,,acc,none,0.7877551020408163,0.026176967197866795,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7897302567435814,0.0072320848578294955,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_stem,5,lm-eval,vllm,yes,acc,none,0.6495401205201395,0.008216767377945324,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_virology,5,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_pt_world_religions,5,lm-eval,vllm,,acc,none,0.8011695906432749,0.030611116557432514,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0bbca0dd2b_2026-09-30T08-55-49.727914.json,1790758209.8252335,1 +v2anneal_120k,global_mmlu_full_ro,5,lm-eval,vllm,yes,acc,none,0.6792479703745905,0.0037628876442344036,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_abstract_algebra,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_astronomy,5,lm-eval,vllm,,acc,none,0.7697368421052632,0.03426059424403165,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_business_ethics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7245283018867924,0.027495663683724022,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_college_biology,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03476590104304133,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7276595744680852,0.029101290698386736,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_econometrics,5,lm-eval,vllm,,acc,none,0.5087719298245614,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7241379310344828,0.037245636197746325,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.02487081525105711,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_formal_logic,5,lm-eval,vllm,,acc,none,0.6031746031746031,0.04375888492727054,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_biology,5,lm-eval,vllm,,acc,none,0.8483870967741935,0.020402616654416734,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6108374384236454,0.03430462416103873,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_geography,5,lm-eval,vllm,,acc,none,0.8232323232323232,0.027178752639044908,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9015544041450777,0.021500249576033463,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.764102564102564,0.02152596540740865,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4740740740740741,0.030444528528810785,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8487394957983193,0.02327425589870791,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_physics,5,lm-eval,vllm,,acc,none,0.5364238410596026,0.04071636065944211,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8477064220183487,0.015405084393157036,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6620370370370371,0.03225941352631297,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8186274509803921,0.027044621719474044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8438818565400844,0.02362715946031866,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_human_aging,5,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_humanities,5,lm-eval,vllm,yes,acc,none,0.620616365568544,0.006693979365863609,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_machine_learning,5,lm-eval,vllm,,acc,none,0.48214285714285715,0.047427623612430116,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_management,5,lm-eval,vllm,,acc,none,0.7961165048543689,0.0398913985953177,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_marketing,5,lm-eval,vllm,,acc,none,0.8931623931623932,0.02023714900899092,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_miscellaneous,5,lm-eval,vllm,,acc,none,0.7739463601532567,0.014957458504335842,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_moral_scenarios,5,lm-eval,vllm,,acc,none,0.41787709497206704,0.01649540063582002,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_other,5,lm-eval,vllm,yes,acc,none,0.7013196009011908,0.007949403879882092,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_philosophy,5,lm-eval,vllm,,acc,none,0.7395498392282959,0.0249267232248456,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_prehistory,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.02277971908873342,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_professional_accounting,5,lm-eval,vllm,,acc,none,0.4787234042553192,0.02980048164562865,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_professional_law,5,lm-eval,vllm,,acc,none,0.5078226857887875,0.012768673076111898,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_professional_medicine,5,lm-eval,vllm,,acc,none,0.6838235294117647,0.028245687391462857,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_professional_psychology,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.01843342764940195,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_public_relations,5,lm-eval,vllm,,acc,none,0.7,0.04389311454644288,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_security_studies,5,lm-eval,vllm,,acc,none,0.7551020408163265,0.02752963744017492,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7816054598635034,0.007316777985487735,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_sociology,5,lm-eval,vllm,,acc,none,0.8258706467661692,0.026814951200421624,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_stem,5,lm-eval,vllm,yes,acc,none,0.6450999048525214,0.008289382940293891,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_ro_world_religions,5,lm-eval,vllm,,acc,none,0.8011695906432749,0.030611116557432514,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c6e253894d_2026-09-30T08-55-59.914110.json,1790758209.793895,1 +v2anneal_120k,global_mmlu_full_sr,5,lm-eval,vllm,yes,acc,none,0.6487679817689788,0.003871306185785417,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_anatomy,5,lm-eval,vllm,,acc,none,0.562962962962963,0.042849586397534056,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_business_ethics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6754716981132075,0.02881561571343209,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_college_biology,5,lm-eval,vllm,,acc,none,0.7361111111111112,0.036856510958975304,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_college_medicine,5,lm-eval,vllm,,acc,none,0.6763005780346821,0.03567603799639168,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_computer_security,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7021276595744681,0.029896145682095487,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_econometrics,5,lm-eval,vllm,,acc,none,0.47368421052631576,0.046970851366478654,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6137931034482759,0.04057324734419032,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6693121693121693,0.02422996529842509,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8258064516129032,0.02157624818451461,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5566502463054187,0.03495334582162933,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7878787878787878,0.031922715695482946,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7929292929292929,0.02886977846026699,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8601036269430051,0.025033870583015143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6974358974358974,0.02329088805377271,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.44814814814814813,0.030321167196316254,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7647058823529411,0.027553614467863825,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5099337748344371,0.040816771072484305,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8348623853211009,0.015919557829976096,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6435185185185185,0.03266478331527272,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.869198312236287,0.02194876605947081,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_human_aging,5,lm-eval,vllm,,acc,none,0.6636771300448431,0.031708824268455046,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7557251908396947,0.037683359597287434,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_humanities,5,lm-eval,vllm,yes,acc,none,0.5934112646121148,0.006835846738958121,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_jurisprudence,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.044531975073749855,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6748466257668712,0.036803503712864595,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_medical_genetics,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_miscellaneous,5,lm-eval,vllm,,acc,none,0.6934865900383141,0.016486952893041595,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7196531791907514,0.024182427496577626,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4547486033519553,0.016653875777524,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_nutrition,5,lm-eval,vllm,,acc,none,0.7124183006535948,0.025917806117147137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_other,5,lm-eval,vllm,yes,acc,none,0.6578693273253943,0.008305556685220664,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_philosophy,5,lm-eval,vllm,,acc,none,0.7106109324758842,0.02575586592263286,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_prehistory,5,lm-eval,vllm,,acc,none,0.6790123456790124,0.025976566010862776,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_professional_accounting,5,lm-eval,vllm,,acc,none,0.44680851063829785,0.02965823509766695,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_professional_law,5,lm-eval,vllm,,acc,none,0.4602346805736636,0.012729785386598602,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6507352941176471,0.02895975519682485,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6699346405228758,0.019023726160724508,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7468313292167695,0.007700641677115095,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_stem,5,lm-eval,vllm,yes,acc,none,0.6267047256581034,0.008351092933103703,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sr_world_religions,5,lm-eval,vllm,,acc,none,0.7485380116959064,0.03327504423846844,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60cdb0eaa7_2026-09-30T16-54-36.828681.json,1790786894.1427798,1 +v2anneal_120k,global_mmlu_full_sv,5,lm-eval,vllm,yes,acc,none,0.6803161942743199,0.003756574953417373,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_anatomy,5,lm-eval,vllm,,acc,none,0.6444444444444445,0.04135176749720385,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_astronomy,5,lm-eval,vllm,,acc,none,0.8157894736842105,0.031546980450822305,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_business_ethics,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7471698113207547,0.02674989977124118,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_college_biology,5,lm-eval,vllm,,acc,none,0.7916666666666666,0.03396116205845331,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_college_medicine,5,lm-eval,vllm,,acc,none,0.6994219653179191,0.03496101481191176,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_college_physics,5,lm-eval,vllm,,acc,none,0.45098039215686275,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_conceptual_physics,5,lm-eval,vllm,,acc,none,0.723404255319149,0.0292418838696288,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_econometrics,5,lm-eval,vllm,,acc,none,0.5526315789473685,0.04677473004491205,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.656084656084656,0.0244644266255964,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_formal_logic,5,lm-eval,vllm,,acc,none,0.5952380952380952,0.043902592653775656,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6157635467980296,0.03422398565657553,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_geography,5,lm-eval,vllm,,acc,none,0.8838383838383839,0.02282888177524936,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8808290155440415,0.02338193534812143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7538461538461538,0.02184086699042312,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4703703703703704,0.030431963547936577,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7983193277310925,0.026064313406304485,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8825688073394495,0.013802780227377303,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03214952147802747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8480392156862745,0.025195658428931827,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_humanities,5,lm-eval,vllm,yes,acc,none,0.6255047821466525,0.006723551555825562,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_jurisprudence,5,lm-eval,vllm,,acc,none,0.75,0.04186091791394607,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6993865030674846,0.036025113188067656,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_machine_learning,5,lm-eval,vllm,,acc,none,0.4732142857142857,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_marketing,5,lm-eval,vllm,,acc,none,0.9017094017094017,0.019503444900757564,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_medical_genetics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_miscellaneous,5,lm-eval,vllm,,acc,none,0.7624521072796935,0.015218733046150228,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_moral_disputes,5,lm-eval,vllm,,acc,none,0.7485549132947977,0.023357365785874006,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4592178770949721,0.016666783616525672,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_nutrition,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.024630048979824716,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_other,5,lm-eval,vllm,yes,acc,none,0.6948825233344061,0.00794694035183702,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_philosophy,5,lm-eval,vllm,,acc,none,0.7266881028938906,0.025311765975426094,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_prehistory,5,lm-eval,vllm,,acc,none,0.7901234567901234,0.022658344085981406,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_professional_accounting,5,lm-eval,vllm,,acc,none,0.4432624113475177,0.02963483847376595,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_professional_law,5,lm-eval,vllm,,acc,none,0.5058670143415906,0.012769356925216389,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_professional_medicine,5,lm-eval,vllm,,acc,none,0.6544117647058824,0.0288881931039887,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_professional_psychology,5,lm-eval,vllm,,acc,none,0.6977124183006536,0.018579232711113967,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_social_sciences,5,lm-eval,vllm,yes,acc,none,0.785830354241144,0.007248688817717436,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_sociology,5,lm-eval,vllm,,acc,none,0.8208955223880597,0.027113286753111865,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_stem,5,lm-eval,vllm,yes,acc,none,0.6447827465905487,0.008238247215245341,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_sv_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/204f9ec9d8_2026-09-30T08-45-30.479931.json,1790757595.9877768,1 +v2anneal_120k,global_mmlu_full_tr,5,lm-eval,vllm,yes,acc,none,0.6360205098988748,0.003866952876590305,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_college_biology,5,lm-eval,vllm,,acc,none,0.7430555555555556,0.03653946969442102,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_college_computer_science,5,lm-eval,vllm,,acc,none,0.59,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_college_medicine,5,lm-eval,vllm,,acc,none,0.6416184971098265,0.0365634365335316,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.676595744680851,0.03057944277361037,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6413793103448275,0.03996629574876715,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6137566137566137,0.02507598176760173,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_formal_logic,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.043435254289490965,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_global_facts,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_biology,5,lm-eval,vllm,,acc,none,0.7935483870967742,0.023025899617188667,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6108374384236454,0.03430462416103873,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7212121212121212,0.03501438706296781,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7929292929292929,0.02886977846026699,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.772020725388601,0.030276909945178256,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6948717948717948,0.02334633529332588,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45185185185185184,0.030343862998512657,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7478991596638656,0.02820554503327774,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8422018348623853,0.015630022970092496,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.625,0.033016908987210894,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8284313725490197,0.026460569561240675,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_human_aging,5,lm-eval,vllm,,acc,none,0.6681614349775785,0.03160295143776678,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_humanities,5,lm-eval,vllm,yes,acc,none,0.5666312433581296,0.006733571872640295,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_jurisprudence,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.044531975073749855,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6748466257668712,0.036803503712864595,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_machine_learning,5,lm-eval,vllm,,acc,none,0.5357142857142857,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_medical_genetics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7330779054916986,0.015818450894777576,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.02454761779480379,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.29832402234636873,0.015301840045129371,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_nutrition,5,lm-eval,vllm,,acc,none,0.6895424836601307,0.026493033225145922,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_other,5,lm-eval,vllm,yes,acc,none,0.664306404892179,0.008250330437027453,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_philosophy,5,lm-eval,vllm,,acc,none,0.707395498392283,0.02583989833487794,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_prehistory,5,lm-eval,vllm,,acc,none,0.7160493827160493,0.02508947852376511,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_professional_accounting,5,lm-eval,vllm,,acc,none,0.4645390070921986,0.029752389657427127,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_professional_law,5,lm-eval,vllm,,acc,none,0.46936114732724904,0.012746237711716587,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6397058823529411,0.02916312857067069,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6470588235294118,0.019333142020797084,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_security_studies,5,lm-eval,vllm,,acc,none,0.746938775510204,0.027833023871399704,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.734481637959051,0.007831469203283299,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_sociology,5,lm-eval,vllm,,acc,none,0.7860696517412935,0.028996909693328965,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_stem,5,lm-eval,vllm,yes,acc,none,0.615604186489058,0.008433375768968663,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_virology,5,lm-eval,vllm,,acc,none,0.5,0.03892494720807614,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_tr_world_religions,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.03188578017686397,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8bc1921df3_2026-09-30T08-55-43.945981.json,1790758207.4713259,1 +v2anneal_120k,global_mmlu_full_uk,5,lm-eval,vllm,yes,acc,none,0.6465603190428714,0.0038462323193176806,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_abstract_algebra,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_anatomy,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.04292596718256977,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6943396226415094,0.028353298073322628,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_college_biology,5,lm-eval,vllm,,acc,none,0.7291666666666666,0.03716177437566019,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_college_chemistry,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_college_computer_science,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_college_medicine,5,lm-eval,vllm,,acc,none,0.6936416184971098,0.035149425512674394,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7319148936170212,0.028957342788342354,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_econometrics,5,lm-eval,vllm,,acc,none,0.47368421052631576,0.046970851366478654,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.040434618619167494,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6455026455026455,0.024636830602842035,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_global_facts,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_biology,5,lm-eval,vllm,,acc,none,0.8096774193548387,0.02233170761182313,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6009852216748769,0.03445487686264716,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_geography,5,lm-eval,vllm,,acc,none,0.8131313131313131,0.02777253333421894,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.717948717948718,0.02281581309889655,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.43703703703703706,0.030242862397654047,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7899159663865546,0.026461398717471864,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_physics,5,lm-eval,vllm,,acc,none,0.4966887417218543,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8403669724770643,0.015703498348461794,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6620370370370371,0.03225941352631297,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.02675640153807894,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8016877637130801,0.02595502084162111,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_human_aging,5,lm-eval,vllm,,acc,none,0.7040358744394619,0.03063659134869978,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_human_sexuality,5,lm-eval,vllm,,acc,none,0.7709923664122137,0.036853466317118506,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_humanities,5,lm-eval,vllm,yes,acc,none,0.5774707757704569,0.006797581752806713,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6809815950920245,0.03661997551073836,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_medical_genetics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_miscellaneous,5,lm-eval,vllm,,acc,none,0.6947637292464879,0.016467711947635053,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_moral_disputes,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.02378620325550823,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_moral_scenarios,5,lm-eval,vllm,,acc,none,0.35195530726256985,0.015972668523689174,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_nutrition,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.025360603796242578,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_other,5,lm-eval,vllm,yes,acc,none,0.6652719665271967,0.008234543068386576,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_philosophy,5,lm-eval,vllm,,acc,none,0.6945337620578779,0.026160584450140488,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_prehistory,5,lm-eval,vllm,,acc,none,0.691358024691358,0.025702640260603798,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_professional_accounting,5,lm-eval,vllm,,acc,none,0.4219858156028369,0.029462189233370586,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_professional_law,5,lm-eval,vllm,,acc,none,0.47522816166883963,0.012754553719781769,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_professional_medicine,5,lm-eval,vllm,,acc,none,0.6580882352941176,0.02881472242225415,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_professional_psychology,5,lm-eval,vllm,,acc,none,0.6437908496732027,0.01937333242072444,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_security_studies,5,lm-eval,vllm,,acc,none,0.7755102040816326,0.02671143055553837,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7536561585960351,0.007593986532701041,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_stem,5,lm-eval,vllm,yes,acc,none,0.6267047256581034,0.008352252974326808,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_virology,5,lm-eval,vllm,,acc,none,0.5060240963855421,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_mmlu_full_uk_world_religions,5,lm-eval,vllm,,acc,none,0.7426900584795322,0.03352799844161867,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8d3e7d4635_2026-09-30T08-30-05.243171.json,1790756654.9122477,1 +v2anneal_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2742a66b0_2026-09-30T07-34-23.323292.json,1790753498.250096,1 +v2anneal_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2742a66b0_2026-09-30T07-34-23.323292.json,1790753498.250096,1 +v2anneal_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_norm,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2742a66b0_2026-09-30T07-34-23.323292.json,1790753498.250096,1 +v2anneal_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/79b292dc6b_2026-09-30T07-38-28.423728.json,1790753749.2418041,1 +v2anneal_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/79b292dc6b_2026-09-30T07-38-28.423728.json,1790753749.2418041,1 +v2anneal_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_norm,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/79b292dc6b_2026-09-30T07-38-28.423728.json,1790753749.2418041,1 +v2anneal_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/63b3a0b294_2026-09-30T07-44-31.920137.json,1790754113.915074,1 +v2anneal_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/63b3a0b294_2026-09-30T07-44-31.920137.json,1790754113.915074,1 +v2anneal_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/63b3a0b294_2026-09-30T07-44-31.920137.json,1790754113.915074,1 +v2anneal_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4924bbb6d0_2026-09-30T08-14-13.642642.json,1790755618.6044626,1 +v2anneal_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4924bbb6d0_2026-09-30T08-14-13.642642.json,1790755618.6044626,1 +v2anneal_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4924bbb6d0_2026-09-30T08-14-13.642642.json,1790755618.6044626,1 +v2anneal_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/840820d405_2026-09-30T08-21-06.214459.json,1790756304.2545533,1 +v2anneal_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_bytes,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/840820d405_2026-09-30T08-21-06.214459.json,1790756304.2545533,1 +v2anneal_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/840820d405_2026-09-30T08-21-06.214459.json,1790756304.2545533,1 +v2anneal_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/833f7e32e8_2026-09-30T07-44-44.398421.json,1790754119.8761442,1 +v2anneal_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/833f7e32e8_2026-09-30T07-44-44.398421.json,1790754119.8761442,1 +v2anneal_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_norm,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/833f7e32e8_2026-09-30T07-44-44.398421.json,1790754119.8761442,1 +v2anneal_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bfe6bbf2d5_2026-09-30T07-34-09.656418.json,1790753469.4275866,1 +v2anneal_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bfe6bbf2d5_2026-09-30T07-34-09.656418.json,1790753469.4275866,1 +v2anneal_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_norm,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bfe6bbf2d5_2026-09-30T07-34-09.656418.json,1790753469.4275866,1 +v2anneal_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/80121a87ef_2026-09-30T08-26-12.160155.json,1790756609.7753644,1 +v2anneal_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_bytes,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/80121a87ef_2026-09-30T08-26-12.160155.json,1790756609.7753644,1 +v2anneal_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_norm,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/80121a87ef_2026-09-30T08-26-12.160155.json,1790756609.7753644,1 +v2anneal_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c5671f1b3f_2026-09-30T07-44-42.287808.json,1790754113.237653,1 +v2anneal_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c5671f1b3f_2026-09-30T07-44-42.287808.json,1790754113.237653,1 +v2anneal_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c5671f1b3f_2026-09-30T07-44-42.287808.json,1790754113.237653,1 +v2anneal_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5ceebe7d29_2026-09-30T08-22-50.495124.json,1790756402.4216914,1 +v2anneal_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5ceebe7d29_2026-09-30T08-22-50.495124.json,1790756402.4216914,1 +v2anneal_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5ceebe7d29_2026-09-30T08-22-50.495124.json,1790756402.4216914,1 +v2anneal_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/36e0bc56df_2026-09-30T08-14-09.446609.json,1790755619.031715,1 +v2anneal_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/36e0bc56df_2026-09-30T08-14-09.446609.json,1790755619.031715,1 +v2anneal_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/36e0bc56df_2026-09-30T08-14-09.446609.json,1790755619.031715,1 +v2anneal_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c68f87c76_2026-09-30T07-34-34.064015.json,1790753514.0559473,1 +v2anneal_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_bytes,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c68f87c76_2026-09-30T07-34-34.064015.json,1790753514.0559473,1 +v2anneal_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0c68f87c76_2026-09-30T07-34-34.064015.json,1790753514.0559473,1 +v2anneal_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/91be30ef53_2026-09-30T08-25-53.461396.json,1790756521.8708394,1 +v2anneal_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/91be30ef53_2026-09-30T08-25-53.461396.json,1790756521.8708394,1 +v2anneal_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/91be30ef53_2026-09-30T08-25-53.461396.json,1790756521.8708394,1 +v2anneal_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2ad0f947e_2026-09-30T08-52-13.524323.json,1790758110.2966776,1 +v2anneal_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2ad0f947e_2026-09-30T08-52-13.524323.json,1790758110.2966776,1 +v2anneal_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b2ad0f947e_2026-09-30T08-52-13.524323.json,1790758110.2966776,1 +v2anneal_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2873c7e9bd_2026-09-30T08-16-52.509147.json,1790756045.7483003,1 +v2anneal_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_bytes,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2873c7e9bd_2026-09-30T08-16-52.509147.json,1790756045.7483003,1 +v2anneal_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_norm,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2873c7e9bd_2026-09-30T08-16-52.509147.json,1790756045.7483003,1 +v2anneal_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e045906d60_2026-09-30T08-32-53.241466.json,1790757010.362059,1 +v2anneal_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e045906d60_2026-09-30T08-32-53.241466.json,1790757010.362059,1 +v2anneal_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e045906d60_2026-09-30T08-32-53.241466.json,1790757010.362059,1 +v2anneal_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e37413d4b7_2026-09-30T07-40-27.169106.json,1790753865.9279923,1 +v2anneal_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_bytes,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e37413d4b7_2026-09-30T07-40-27.169106.json,1790753865.9279923,1 +v2anneal_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_norm,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e37413d4b7_2026-09-30T07-40-27.169106.json,1790753865.9279923,1 +v2anneal_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f9d8d59099_2026-09-30T08-20-24.847155.json,1790756204.7786026,1 +v2anneal_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f9d8d59099_2026-09-30T08-20-24.847155.json,1790756204.7786026,1 +v2anneal_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_norm,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f9d8d59099_2026-09-30T08-20-24.847155.json,1790756204.7786026,1 +v2anneal_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/234af93d20_2026-09-30T07-34-49.187877.json,1790753515.1355681,1 +v2anneal_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/234af93d20_2026-09-30T07-34-49.187877.json,1790753515.1355681,1 +v2anneal_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/234af93d20_2026-09-30T07-34-49.187877.json,1790753515.1355681,1 +v2anneal_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a9550c2bc6_2026-09-30T08-27-03.489027.json,1790756654.9120932,1 +v2anneal_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a9550c2bc6_2026-09-30T08-27-03.489027.json,1790756654.9120932,1 +v2anneal_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a9550c2bc6_2026-09-30T08-27-03.489027.json,1790756654.9120932,1 +v2anneal_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3fc3097adc_2026-09-30T08-37-26.610842.json,1790757281.022396,1 +v2anneal_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3fc3097adc_2026-09-30T08-37-26.610842.json,1790757281.022396,1 +v2anneal_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3fc3097adc_2026-09-30T08-37-26.610842.json,1790757281.022396,1 +v2anneal_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26fc6af8dc_2026-09-30T08-21-07.787343.json,1790756304.2311845,1 +v2anneal_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26fc6af8dc_2026-09-30T08-21-07.787343.json,1790756304.2311845,1 +v2anneal_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_norm,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26fc6af8dc_2026-09-30T08-21-07.787343.json,1790756304.2311845,1 +v2anneal_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c307e7852_2026-09-30T08-49-20.957848.json,1790757995.5064917,1 +v2anneal_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c307e7852_2026-09-30T08-49-20.957848.json,1790757995.5064917,1 +v2anneal_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c307e7852_2026-09-30T08-49-20.957848.json,1790757995.5064917,1 +v2anneal_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/783959f5af_2026-09-30T08-31-36.390910.json,1790756931.2110164,1 +v2anneal_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/783959f5af_2026-09-30T08-31-36.390910.json,1790756931.2110164,1 +v2anneal_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/783959f5af_2026-09-30T08-31-36.390910.json,1790756931.2110164,1 +v2anneal_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac5b1660b8_2026-09-30T07-44-36.170496.json,1790754112.5478299,1 +v2anneal_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac5b1660b8_2026-09-30T07-44-36.170496.json,1790754112.5478299,1 +v2anneal_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac5b1660b8_2026-09-30T07-44-36.170496.json,1790754112.5478299,1 +v2anneal_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d8d456e8e4_2026-09-30T08-26-55.313880.json,1790756651.919656,1 +v2anneal_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_bytes,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d8d456e8e4_2026-09-30T08-26-55.313880.json,1790756651.919656,1 +v2anneal_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d8d456e8e4_2026-09-30T08-26-55.313880.json,1790756651.919656,1 +v2anneal_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0fb76307f4_2026-09-30T08-45-19.823966.json,1790757747.1804583,1 +v2anneal_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0fb76307f4_2026-09-30T08-45-19.823966.json,1790757747.1804583,1 +v2anneal_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0fb76307f4_2026-09-30T08-45-19.823966.json,1790757747.1804583,1 +v2anneal_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e87f450629_2026-09-30T08-37-23.640945.json,1790757281.1401832,1 +v2anneal_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e87f450629_2026-09-30T08-37-23.640945.json,1790757281.1401832,1 +v2anneal_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e87f450629_2026-09-30T08-37-23.640945.json,1790757281.1401832,1 +v2anneal_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/08d9322aec_2026-09-30T08-32-47.881271.json,1790757007.1889896,1 +v2anneal_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.93,0.02564323999762428,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/08d9322aec_2026-09-30T08-32-47.881271.json,1790757007.1889896,1 +v2anneal_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_norm,none,0.92,0.027265992434429072,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/08d9322aec_2026-09-30T08-32-47.881271.json,1790757007.1889896,1 +v2anneal_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b1174b183c_2026-09-30T07-34-14.320040.json,1790753469.507396,1 +v2anneal_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b1174b183c_2026-09-30T07-34-14.320040.json,1790753469.507396,1 +v2anneal_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b1174b183c_2026-09-30T07-34-14.320040.json,1790753469.507396,1 +v2anneal_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7975a755a_2026-09-30T08-37-25.920039.json,1790757281.045539,1 +v2anneal_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_bytes,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7975a755a_2026-09-30T08-37-25.920039.json,1790757281.045539,1 +v2anneal_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7975a755a_2026-09-30T08-37-25.920039.json,1790757281.045539,1 +v2anneal_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2efb68c3c2_2026-09-30T16-51-06.383456.json,1790786895.427406,1 +v2anneal_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2efb68c3c2_2026-09-30T16-51-06.383456.json,1790786895.427406,1 +v2anneal_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2efb68c3c2_2026-09-30T16-51-06.383456.json,1790786895.427406,1 +v2anneal_120k,global_piqa_prompted_als_latn,0,lm-eval,vllm,,exact_match,strict_match,0.34,0.04760952285695236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bce375b22e_2026-09-30T07-44-39.749531.json,1790754112.5746913,1 +v2anneal_120k,global_piqa_prompted_bos_latn,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.049236596391733084,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/397d20115f_2026-09-30T08-32-30.461657.json,1790756982.7556195,1 +v2anneal_120k,global_piqa_prompted_bul_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.04960449637488584,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0d0ec9daf5_2026-09-30T08-31-38.029932.json,1790756929.0569682,1 +v2anneal_120k,global_piqa_prompted_cat_latn,0,lm-eval,vllm,,exact_match,strict_match,0.35,0.0479372485441102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b61d215beb_2026-09-30T08-17-05.136081.json,1790756056.6785228,1 +v2anneal_120k,global_piqa_prompted_ces_latn,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.04975698519562428,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b76070c117_2026-09-30T08-17-00.354385.json,1790756044.61594,1 +v2anneal_120k,global_piqa_prompted_deu_latn,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.04975698519562428,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/816a5ebf6d_2026-09-30T08-14-19.042858.json,1790755619.446754,1 +v2anneal_120k,global_piqa_prompted_ekk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.3,0.046056618647183814,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f78975ae0d_2026-09-30T08-20-35.025463.json,1790756205.077248,1 +v2anneal_120k,global_piqa_prompted_ell_grek,0,lm-eval,vllm,,exact_match,strict_match,0.29,0.04560480215720684,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2632646f17_2026-09-30T08-11-16.655166.json,1790754237.150687,1 +v2anneal_120k,global_piqa_prompted_eng_latn,0,lm-eval,vllm,,exact_match,strict_match,0.37,0.048523658709391,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6e13c58851_2026-09-30T07-34-39.424026.json,1790753513.6044145,1 +v2anneal_120k,global_piqa_prompted_fin_latn,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.04923659639173309,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3b13b7f09a_2026-09-30T08-49-22.072597.json,1790757994.81424,1 +v2anneal_120k,global_piqa_prompted_fra_latn_fran,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620333,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a67103a8e7_2026-09-30T08-31-36.052166.json,1790756930.3454416,1 +v2anneal_120k,global_piqa_prompted_glg_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.049431107042371025,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/154a5175e5_2026-09-30T08-49-21.047257.json,1790757994.7078502,1 +v2anneal_120k,global_piqa_prompted_hrv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78dae58ed1_2026-09-30T08-14-17.059858.json,1790755619.4818902,1 +v2anneal_120k,global_piqa_prompted_hun_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/97f17d1f74_2026-09-30T07-34-31.586580.json,1790753469.1640487,1 +v2anneal_120k,global_piqa_prompted_isl_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0cd0de4218_2026-09-30T08-26-18.870606.json,1790756611.5903957,1 +v2anneal_120k,global_piqa_prompted_ita_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0a473b0b3_2026-09-30T08-14-13.923744.json,1790755618.9056883,1 +v2anneal_120k,global_piqa_prompted_kat_geor,0,lm-eval,vllm,,exact_match,strict_match,0.07,0.025643239997624283,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4057deaf42_2026-09-30T08-39-19.627576.json,1790757385.491713,1 +v2anneal_120k,global_piqa_prompted_lit_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6c34a0db15_2026-09-30T08-11-17.172019.json,1790754233.995834,1 +v2anneal_120k,global_piqa_prompted_mkd_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.37,0.04852365870939099,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f6a3af5284_2026-09-30T07-38-38.432820.json,1790753750.9444952,1 +v2anneal_120k,global_piqa_prompted_nld_latn,0,lm-eval,vllm,,exact_match,strict_match,0.32,0.04688261722621505,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0663bf9606_2026-09-30T08-27-04.898330.json,1790756653.1883855,1 +v2anneal_120k,global_piqa_prompted_nno_latn,0,lm-eval,vllm,,exact_match,strict_match,0.44,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7ee2c0e759_2026-09-30T08-48-48.910029.json,1790757959.9045625,1 +v2anneal_120k,global_piqa_prompted_nob_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001975,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fc62bfca31_2026-09-30T08-41-43.627119.json,1790757467.6409137,1 +v2anneal_120k,global_piqa_prompted_pol_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f9384a211c_2026-09-30T08-37-30.021810.json,1790757280.8220496,1 +v2anneal_120k,global_piqa_prompted_por_latn_port,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ae5e793fdd_2026-09-30T07-34-39.919773.json,1790753498.2306492,1 +v2anneal_120k,global_piqa_prompted_ron_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.04943110704237102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/712e8221d4_2026-09-30T08-22-52.255002.json,1790756406.0055506,1 +v2anneal_120k,global_piqa_prompted_slk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c05610e62_2026-09-30T08-14-15.511790.json,1790755618.0235023,1 +v2anneal_120k,global_piqa_prompted_slv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9e0f52e9c6_2026-09-30T08-43-38.901126.json,1790757647.7072637,1 +v2anneal_120k,global_piqa_prompted_spa_latn_spai,0,lm-eval,vllm,,exact_match,strict_match,0.48,0.050211673156867795,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/461c6d7d3b_2026-09-30T08-52-51.632329.json,1790758208.568163,1 +v2anneal_120k,global_piqa_prompted_srp_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.4,0.04923659639173309,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/58414f4b03_2026-09-30T07-34-48.980088.json,1790753513.601634,1 +v2anneal_120k,global_piqa_prompted_swe_latn,0,lm-eval,vllm,,exact_match,strict_match,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/47d929537c_2026-09-30T08-47-30.821358.json,1790757887.3143518,1 +v2anneal_120k,global_piqa_prompted_tur_latn,0,lm-eval,vllm,,exact_match,strict_match,0.39,0.04902071300001975,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/45525e4a60_2026-09-30T08-31-32.830931.json,1790756929.319447,1 +v2anneal_120k,global_piqa_prompted_ukr_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7706f2b918_2026-09-30T08-33-22.276808.json,1790757024.090673,1 +v2anneal_120k,gsm8k,4,lm-eval,vllm,,exact_match,flexible-extract,0.8248673237300985,0.010469307043157896,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/df7559c0a8_2026-09-30T08-12-00.352428.json,1790754224.8933513,1 +v2anneal_120k,gsm8k,4,lm-eval,vllm,,exact_match,strict-match,0.8218347232752085,0.010540132527549465,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/df7559c0a8_2026-09-30T08-12-00.352428.json,1790754224.8933513,1 +v2anneal_120k,hellaswag,0,lm-eval,vllm,,acc,none,0.6094403505277833,0.004868787333436616,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/90ed463fa8_2026-09-30T08-15-38.767205.json,1790755619.2456968,1 +v2anneal_120k,hellaswag,0,lm-eval,vllm,,acc_norm,none,0.8001394144592711,0.003990781278700381,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/90ed463fa8_2026-09-30T08-15-38.767205.json,1790755619.2456968,1 +v2anneal_120k,hellaswag,10,lm-eval,vllm,,acc,none,0.632244572794264,0.004812088620277034,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/62aeb64f3a_2026-09-30T08-16-16.383565.json,1790754118.4044855,1 +v2anneal_120k,hellaswag,10,lm-eval,vllm,,acc_norm,none,0.8301135232025493,0.0037476555337545773,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/62aeb64f3a_2026-09-30T08-16-16.383565.json,1790754118.4044855,1 +v2anneal_120k,hellaswag_ca,0,lm-eval,vllm,,acc,none,0.5085224188470308,0.005209272701845509,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7cf016755_2026-09-30T08-28-15.172504.json,1790756644.8667934,1 +v2anneal_120k,hellaswag_ca,0,lm-eval,vllm,,acc_norm,none,0.6670285528172837,0.004910728162964033,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b7cf016755_2026-09-30T08-28-15.172504.json,1790756644.8667934,1 +v2anneal_120k,hellaswag_da,0,lm-eval,vllm,,acc,none,0.538527673293928,0.00516823190899877,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed8f84f0c5_2026-09-30T08-15-41.449503.json,1790755619.3633385,1 +v2anneal_120k,hellaswag_da,0,lm-eval,vllm,,acc_norm,none,0.6967221923696937,0.004765574762726751,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed8f84f0c5_2026-09-30T08-15-41.449503.json,1790755619.3633385,1 +v2anneal_120k,hellaswag_de,0,lm-eval,vllm,,acc,none,0.5308497011101623,0.005156339773239881,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d433c1f584_2026-09-30T07-42-05.796758.json,1790753873.5420372,1 +v2anneal_120k,hellaswag_de,0,lm-eval,vllm,,acc_norm,none,0.6891545687446626,0.004782228287116277,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d433c1f584_2026-09-30T07-42-05.796758.json,1790753873.5420372,1 +v2anneal_120k,hellaswag_es,0,lm-eval,vllm,,acc,none,0.5648602517601877,0.005120891534898503,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9b1d836ba5_2026-09-30T08-54-52.399325.json,1790758235.158873,1 +v2anneal_120k,hellaswag_es,0,lm-eval,vllm,,acc_norm,none,0.7402389588222744,0.004529326922991129,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9b1d836ba5_2026-09-30T08-54-52.399325.json,1790758235.158873,1 +v2anneal_120k,hellaswag_eu,0,lm-eval,vllm,,acc,none,0.29983792544570503,0.004762969779745698,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/cdd651a216_2026-09-30T08-16-40.989334.json,1790755924.982935,1 +v2anneal_120k,hellaswag_eu,0,lm-eval,vllm,,acc_norm,none,0.36175040518638574,0.004994994788213977,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/cdd651a216_2026-09-30T08-16-40.989334.json,1790755924.982935,1 +v2anneal_120k,hellaswag_fr,0,lm-eval,vllm,,acc,none,0.5541871921182266,0.005143998502778556,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9dc5b2b749_2026-09-30T08-46-54.343751.json,1790757746.2377396,1 +v2anneal_120k,hellaswag_fr,0,lm-eval,vllm,,acc_norm,none,0.7255300920968087,0.004618185824360283,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9dc5b2b749_2026-09-30T08-46-54.343751.json,1790757746.2377396,1 +v2anneal_120k,hellaswag_hr,0,lm-eval,vllm,,acc,none,0.4960405448210326,0.005137849721301563,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b055b2ebcc_2026-09-30T08-22-34.981676.json,1790756304.2756293,1 +v2anneal_120k,hellaswag_hr,0,lm-eval,vllm,,acc_norm,none,0.6601203674374406,0.004867423638391813,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b055b2ebcc_2026-09-30T08-22-34.981676.json,1790756304.2756293,1 +v2anneal_120k,hellaswag_hu,0,lm-eval,vllm,,acc,none,0.4459918850751179,0.005205611432301113,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/06c8a9ec68_2026-09-30T08-22-46.566573.json,1790756302.5520985,1 +v2anneal_120k,hellaswag_hu,0,lm-eval,vllm,,acc_norm,none,0.5801074679241145,0.0051686069776874085,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/06c8a9ec68_2026-09-30T08-22-46.566573.json,1790756302.5520985,1 +v2anneal_120k,hellaswag_it,0,lm-eval,vllm,,acc,none,0.5344283694115087,0.005202750487887637,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e5b097ac29_2026-09-30T08-12-31.103542.json,1790754231.90667,1 +v2anneal_120k,hellaswag_it,0,lm-eval,vllm,,acc_norm,none,0.7060807135864244,0.004751559904731701,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e5b097ac29_2026-09-30T08-12-31.103542.json,1790754231.90667,1 +v2anneal_120k,hellaswag_nl,0,lm-eval,vllm,,acc,none,0.5327576902320561,0.005183661951081025,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1d5c07a42a_2026-09-30T07-35-34.910569.json,1790753469.3869572,1 +v2anneal_120k,hellaswag_nl,0,lm-eval,vllm,,acc_norm,none,0.6953049109552077,0.00478212696566229,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1d5c07a42a_2026-09-30T07-35-34.910569.json,1790753469.3869572,1 +v2anneal_120k,hellaswag_pt,0,lm-eval,vllm,,acc,none,0.5479466897822083,0.005180959385457814,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c222073ef_2026-09-30T08-33-01.288789.json,1790756930.4788506,1 +v2anneal_120k,hellaswag_pt,0,lm-eval,vllm,,acc_norm,none,0.7206631270993608,0.004670641044834582,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c222073ef_2026-09-30T08-33-01.288789.json,1790756930.4788506,1 +v2anneal_120k,hellaswag_ro,0,lm-eval,vllm,,acc,none,0.5163872363439698,0.00519764553349342,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d33cf24f4d_2026-09-30T08-22-48.248347.json,1790756304.2128713,1 +v2anneal_120k,hellaswag_ro,0,lm-eval,vllm,,acc_norm,none,0.6697674418604651,0.004891499259185562,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d33cf24f4d_2026-09-30T08-22-48.248347.json,1790756304.2128713,1 +v2anneal_120k,hellaswag_sk,0,lm-eval,vllm,,acc,none,0.47221929362150766,0.005126286162723778,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/21e88b8133_2026-09-30T08-15-44.516015.json,1790755619.5046027,1 +v2anneal_120k,hellaswag_sk,0,lm-eval,vllm,,acc_norm,none,0.6133895624670532,0.005000451341117208,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/21e88b8133_2026-09-30T08-15-44.516015.json,1790755619.5046027,1 +v2anneal_120k,hellaswag_sr,0,lm-eval,vllm,,acc,none,0.49857127738385015,0.005143968364677214,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/25189a1c49_2026-09-30T08-28-26.565139.json,1790756648.4586253,1 +v2anneal_120k,hellaswag_sr,0,lm-eval,vllm,,acc_norm,none,0.6534024764525347,0.004895907156155269,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/25189a1c49_2026-09-30T08-28-26.565139.json,1790756648.4586253,1 +v2anneal_120k,hellaswag_sv,0,lm-eval,vllm,,acc,none,0.5310238982679237,0.00522529918123481,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e4d13cb1e6_2026-09-30T07-36-09.835275.json,1790753513.6272507,1 +v2anneal_120k,hellaswag_sv,0,lm-eval,vllm,,acc_norm,none,0.7042315281736461,0.004778729445632501,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e4d13cb1e6_2026-09-30T07-36-09.835275.json,1790753513.6272507,1 +v2anneal_120k,hellaswag_uk,0,lm-eval,vllm,,acc,none,0.4667871187161229,0.005143527822058997,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/99e03c17d8_2026-09-30T08-49-09.803919.json,1790757886.574674,1 +v2anneal_120k,hellaswag_uk,0,lm-eval,vllm,,acc_norm,none,0.6068657668190031,0.005035795633020201,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/99e03c17d8_2026-09-30T08-49-09.803919.json,1790757886.574674,1 +v2anneal_120k,ifeval,0,lm-eval,vllm,,inst_level_loose_acc,none,0.44364508393285373,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69b44d6b54_2026-09-30T07-36-01.976399.json,1790753496.2781277,1 +v2anneal_120k,ifeval,0,lm-eval,vllm,,inst_level_strict_acc,none,0.4184652278177458,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69b44d6b54_2026-09-30T07-36-01.976399.json,1790753496.2781277,1 +v2anneal_120k,ifeval,0,lm-eval,vllm,,prompt_level_loose_acc,none,0.2975970425138632,0.019674812004413393,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69b44d6b54_2026-09-30T07-36-01.976399.json,1790753496.2781277,1 +v2anneal_120k,ifeval,0,lm-eval,vllm,,prompt_level_strict_acc,none,0.2735674676524954,0.019183727107392846,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69b44d6b54_2026-09-30T07-36-01.976399.json,1790753496.2781277,1 +v2anneal_120k,include_base_44_albanian,0,lm-eval,vllm,yes,acc,none,0.7404718693284936,0.018709782815849715,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 +v2anneal_120k,include_base_44_albanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.7488789237668162,0.029105220833224605,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 +v2anneal_120k,include_base_44_albanian_business_commerce,0,lm-eval,vllm,,acc,none,0.726457399103139,0.029918586707798872,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 +v2anneal_120k,include_base_44_albanian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 +v2anneal_120k,include_base_44_albanian_social_science,0,lm-eval,vllm,,acc,none,0.8181818181818182,0.0524863881081478,55,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 +v2anneal_120k,include_base_44_albanian_stem,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6784d33016_2026-09-30T08-52-16.791886.json,1790758108.9468808,1 +v2anneal_120k,include_base_44_basque,0,lm-eval,vllm,yes,acc,none,0.456,0.02229623834840707,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d2dbe40f12_2026-09-30T08-47-32.827069.json,1790757888.5945458,1 +v2anneal_120k,include_base_44_basque_professional_certification,0,lm-eval,vllm,,acc,none,0.456,0.02229623834840707,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d2dbe40f12_2026-09-30T08-47-32.827069.json,1790757888.5945458,1 +v2anneal_120k,include_base_44_bulgarian,0,lm-eval,vllm,yes,acc,none,0.6854545454545454,0.01961876977892238,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4705518c29_2026-09-30T08-43-29.717376.json,1790757643.804846,1 +v2anneal_120k,include_base_44_bulgarian_arts_humanities,0,lm-eval,vllm,,acc,none,0.76,0.027065293652238982,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4705518c29_2026-09-30T08-43-29.717376.json,1790757643.804846,1 +v2anneal_120k,include_base_44_bulgarian_social_science,0,lm-eval,vllm,,acc,none,0.636,0.030491555220405475,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4705518c29_2026-09-30T08-43-29.717376.json,1790757643.804846,1 +v2anneal_120k,include_base_44_bulgarian_stem,0,lm-eval,vllm,,acc,none,0.56,0.07091242083423346,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4705518c29_2026-09-30T08-43-29.717376.json,1790757643.804846,1 +v2anneal_120k,include_base_44_croatian,0,lm-eval,vllm,yes,acc,none,0.7381818181818182,0.0187117067834429,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c3d68932e_2026-09-30T08-48-47.341561.json,1790757959.9321353,1 +v2anneal_120k,include_base_44_croatian_arts_humanities,0,lm-eval,vllm,,acc,none,0.7,0.029040893477575786,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c3d68932e_2026-09-30T08-48-47.341561.json,1790757959.9321353,1 +v2anneal_120k,include_base_44_croatian_social_science,0,lm-eval,vllm,,acc,none,0.784,0.02607865766373279,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c3d68932e_2026-09-30T08-48-47.341561.json,1790757959.9321353,1 +v2anneal_120k,include_base_44_croatian_stem,0,lm-eval,vllm,,acc,none,0.7,0.06546536707079771,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3c3d68932e_2026-09-30T08-48-47.341561.json,1790757959.9321353,1 +v2anneal_120k,include_base_44_dutch,0,lm-eval,vllm,yes,acc,none,0.7096188747731398,0.01928875003389857,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 +v2anneal_120k,include_base_44_dutch_applied_science,0,lm-eval,vllm,,acc,none,0.9333333333333333,0.06666666666666665,15,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 +v2anneal_120k,include_base_44_dutch_arts_humanities,0,lm-eval,vllm,,acc,none,0.7325102880658436,0.028454615592677018,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 +v2anneal_120k,include_base_44_dutch_health_oriented_education,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 +v2anneal_120k,include_base_44_dutch_social_science,0,lm-eval,vllm,,acc,none,0.6954732510288066,0.029583207218060927,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 +v2anneal_120k,include_base_44_dutch_stem,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd2f34bce5_2026-09-30T07-34-14.013279.json,1790753469.457185,1 +v2anneal_120k,include_base_44_estonian,0,lm-eval,vllm,yes,acc,none,0.5758928571428571,0.0325273790057567,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 +v2anneal_120k,include_base_44_estonian_applied_science,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.09705231721239392,14,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 +v2anneal_120k,include_base_44_estonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.515527950310559,0.03950940416210684,161,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 +v2anneal_120k,include_base_44_estonian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5,0.5,2,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 +v2anneal_120k,include_base_44_estonian_social_science,0,lm-eval,vllm,,acc,none,0.5454545454545454,0.1574591643244434,11,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 +v2anneal_120k,include_base_44_estonian_stem,0,lm-eval,vllm,,acc,none,0.75,0.07319250547113999,36,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/addae7a41c_2026-09-30T08-21-09.487771.json,1790756304.3192394,1 +v2anneal_120k,include_base_44_finnish,0,lm-eval,vllm,yes,acc,none,0.5263157894736842,0.02109254822268859,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 +v2anneal_120k,include_base_44_finnish_applied_science,0,lm-eval,vllm,,acc,none,0.4482758620689655,0.09398415777506855,29,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 +v2anneal_120k,include_base_44_finnish_arts_humanities,0,lm-eval,vllm,,acc,none,0.4424778761061947,0.03311201227233577,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 +v2anneal_120k,include_base_44_finnish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6222222222222222,0.07309112127323451,45,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 +v2anneal_120k,include_base_44_finnish_social_science,0,lm-eval,vllm,,acc,none,0.584070796460177,0.032858761806830256,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 +v2anneal_120k,include_base_44_finnish_stem,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4b800da094_2026-09-30T07-34-20.800941.json,1790753469.4142418,1 +v2anneal_120k,include_base_44_french,0,lm-eval,vllm,yes,acc,none,0.5871121718377088,0.023751693706955852,419,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 +v2anneal_120k,include_base_44_french_arts_humanities,0,lm-eval,vllm,,acc,none,0.6466165413533834,0.029364565335867333,266,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 +v2anneal_120k,include_base_44_french_driving_license,0,lm-eval,vllm,,acc,none,0.3829787234042553,0.0716734777251339,47,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 +v2anneal_120k,include_base_44_french_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5625,0.128086884574495,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 +v2anneal_120k,include_base_44_french_social_science,0,lm-eval,vllm,,acc,none,0.5540540540540541,0.05817759292339765,74,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 +v2anneal_120k,include_base_44_french_stem,0,lm-eval,vllm,,acc,none,0.375,0.125,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4044931f90_2026-09-30T07-44-40.462854.json,1790754113.7397146,1 +v2anneal_120k,include_base_44_georgian,0,lm-eval,vllm,yes,acc,none,0.47,0.0223427481925028,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/320792eefb_2026-09-30T08-11-18.728761.json,1790754232.3812442,1 +v2anneal_120k,include_base_44_georgian_arts_humanities,0,lm-eval,vllm,,acc,none,0.47,0.0223427481925028,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/320792eefb_2026-09-30T08-11-18.728761.json,1790754232.3812442,1 +v2anneal_120k,include_base_44_german,0,lm-eval,vllm,yes,acc,none,0.5539568345323741,0.04247861636666499,139,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1af60b0859_2026-09-30T08-15-11.795544.json,1790755924.968859,1 +v2anneal_120k,include_base_44_german_driving_license,0,lm-eval,vllm,,acc,none,0.4782608695652174,0.10649955403405124,23,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1af60b0859_2026-09-30T08-15-11.795544.json,1790755924.968859,1 +v2anneal_120k,include_base_44_german_social_science,0,lm-eval,vllm,,acc,none,0.5824175824175825,0.05198368783767558,91,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1af60b0859_2026-09-30T08-15-11.795544.json,1790755924.968859,1 +v2anneal_120k,include_base_44_german_stem,0,lm-eval,vllm,,acc,none,0.52,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1af60b0859_2026-09-30T08-15-11.795544.json,1790755924.968859,1 +v2anneal_120k,include_base_44_greek,0,lm-eval,vllm,yes,acc,none,0.5561594202898551,0.021018339570042663,552,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 +v2anneal_120k,include_base_44_greek_arts_humanities,0,lm-eval,vllm,,acc,none,0.6216216216216216,0.08083044344561424,37,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 +v2anneal_120k,include_base_44_greek_business_commerce,0,lm-eval,vllm,,acc,none,0.7301587301587301,0.05637245937794517,63,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 +v2anneal_120k,include_base_44_greek_health_oriented_education,0,lm-eval,vllm,,acc,none,0.4,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 +v2anneal_120k,include_base_44_greek_medical_license,0,lm-eval,vllm,,acc,none,0.5298507462686567,0.043278164192160934,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 +v2anneal_120k,include_base_44_greek_professional_certification,0,lm-eval,vllm,,acc,none,0.4925373134328358,0.04335066912520509,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 +v2anneal_120k,include_base_44_greek_social_science,0,lm-eval,vllm,,acc,none,0.5746268656716418,0.04286987049655245,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 +v2anneal_120k,include_base_44_greek_stem,0,lm-eval,vllm,,acc,none,0.56,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/804f4304df_2026-09-30T08-16-56.821839.json,1790756043.8260484,1 +v2anneal_120k,include_base_44_hungarian,0,lm-eval,vllm,yes,acc,none,0.4690909090909091,0.021315519716048476,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cabf9c92e_2026-09-30T07-34-11.753188.json,1790753468.5730548,1 +v2anneal_120k,include_base_44_hungarian_applied_science,0,lm-eval,vllm,,acc,none,0.45161290322580644,0.02698903311400244,341,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cabf9c92e_2026-09-30T07-34-11.753188.json,1790753468.5730548,1 +v2anneal_120k,include_base_44_hungarian_social_science,0,lm-eval,vllm,,acc,none,0.5,0.03696106354772864,184,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cabf9c92e_2026-09-30T07-34-11.753188.json,1790753468.5730548,1 +v2anneal_120k,include_base_44_hungarian_stem,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cabf9c92e_2026-09-30T07-34-11.753188.json,1790753468.5730548,1 +v2anneal_120k,include_base_44_italian,0,lm-eval,vllm,yes,acc,none,0.7135036496350365,0.019273755977909514,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 +v2anneal_120k,include_base_44_italian_applied_science,0,lm-eval,vllm,,acc,none,0.7714285714285715,0.0720144043214405,35,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 +v2anneal_120k,include_base_44_italian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6706586826347305,0.03647706112341117,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 +v2anneal_120k,include_base_44_italian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.75,0.1305582419667734,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 +v2anneal_120k,include_base_44_italian_professional_certification,0,lm-eval,vllm,,acc,none,0.6774193548387096,0.03766930374975111,155,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 +v2anneal_120k,include_base_44_italian_social_science,0,lm-eval,vllm,,acc,none,0.7844311377245509,0.031916582528798025,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 +v2anneal_120k,include_base_44_italian_stem,0,lm-eval,vllm,,acc,none,0.5833333333333334,0.1486470975026408,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/daefce61bf_2026-09-30T08-37-26.836509.json,1790757281.0503442,1 +v2anneal_120k,include_base_44_lithuanian,0,lm-eval,vllm,yes,acc,none,0.6292134831460674,0.020827616929200387,534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 +v2anneal_120k,include_base_44_lithuanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6208955223880597,0.02654700230415632,335,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 +v2anneal_120k,include_base_44_lithuanian_business_commerce,0,lm-eval,vllm,,acc,none,0.5,0.08006407690254357,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 +v2anneal_120k,include_base_44_lithuanian_professional_certification,0,lm-eval,vllm,,acc,none,0.6666666666666666,0.0687614164172529,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 +v2anneal_120k,include_base_44_lithuanian_social_science,0,lm-eval,vllm,,acc,none,0.6233766233766234,0.055580454819565604,77,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 +v2anneal_120k,include_base_44_lithuanian_stem,0,lm-eval,vllm,,acc,none,0.8235294117647058,0.06636189115503133,34,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5ccd178e5_2026-09-30T08-41-41.397173.json,1790757467.758124,1 +v2anneal_120k,include_base_44_north macedonian,0,lm-eval,vllm,yes,acc,none,0.8148820326678766,0.016447155294872257,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 +v2anneal_120k,include_base_44_north macedonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.023432852220591778,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 +v2anneal_120k,include_base_44_north macedonian_business_commerce,0,lm-eval,vllm,,acc,none,0.78125,0.027683220663030285,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 +v2anneal_120k,include_base_44_north macedonian_social_science,0,lm-eval,vllm,,acc,none,0.8867924528301887,0.04393868070601046,53,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 +v2anneal_120k,include_base_44_north macedonian_stem,0,lm-eval,vllm,,acc,none,0.7,0.06546536707079771,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0e44a10fc3_2026-09-30T08-26-17.312781.json,1790756611.589398,1 +v2anneal_120k,include_base_44_polish,0,lm-eval,vllm,yes,acc,none,0.5109489051094891,0.021320189652018123,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fb24c7bd9d_2026-09-30T08-20-34.086249.json,1790756205.4627898,1 +v2anneal_120k,include_base_44_polish_professional_certification,0,lm-eval,vllm,,acc,none,0.5221774193548387,0.022451211394315496,496,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fb24c7bd9d_2026-09-30T08-20-34.086249.json,1790756205.4627898,1 +v2anneal_120k,include_base_44_polish_social_science,0,lm-eval,vllm,,acc,none,0.75,0.25,4,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fb24c7bd9d_2026-09-30T08-20-34.086249.json,1790756205.4627898,1 +v2anneal_120k,include_base_44_polish_stem,0,lm-eval,vllm,,acc,none,0.375,0.07061658535825402,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fb24c7bd9d_2026-09-30T08-20-34.086249.json,1790756205.4627898,1 +v2anneal_120k,include_base_44_portuguese,0,lm-eval,vllm,yes,acc,none,0.6079854809437386,0.020533974972543202,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 +v2anneal_120k,include_base_44_portuguese_applied_science,0,lm-eval,vllm,,acc,none,0.5,0.05488212999484517,84,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 +v2anneal_120k,include_base_44_portuguese_arts_humanities,0,lm-eval,vllm,,acc,none,0.6233766233766234,0.03917267027864407,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 +v2anneal_120k,include_base_44_portuguese_business_commerce,0,lm-eval,vllm,,acc,none,0.4861111111111111,0.05931618532716555,72,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 +v2anneal_120k,include_base_44_portuguese_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6612903225806451,0.060596141174796975,62,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 +v2anneal_120k,include_base_44_portuguese_social_science,0,lm-eval,vllm,,acc,none,0.7142857142857143,0.03652214232606526,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 +v2anneal_120k,include_base_44_portuguese_stem,0,lm-eval,vllm,,acc,none,0.44,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/948cab35e0_2026-09-30T08-32-52.735276.json,1790757005.5898197,1 +v2anneal_120k,include_base_44_serbian,0,lm-eval,vllm,yes,acc,none,0.6709090909090909,0.01992791368582081,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5b32a3000_2026-09-30T08-43-21.758999.json,1790757642.9029405,1 +v2anneal_120k,include_base_44_serbian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6293929712460063,0.02734264180492097,313,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5b32a3000_2026-09-30T08-43-21.758999.json,1790757642.9029405,1 +v2anneal_120k,include_base_44_serbian_social_science,0,lm-eval,vllm,,acc,none,0.7540106951871658,0.031578419772456075,187,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5b32a3000_2026-09-30T08-43-21.758999.json,1790757642.9029405,1 +v2anneal_120k,include_base_44_serbian_stem,0,lm-eval,vllm,,acc,none,0.62,0.06934092056863769,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b5b32a3000_2026-09-30T08-43-21.758999.json,1790757642.9029405,1 +v2anneal_120k,include_base_44_spanish,0,lm-eval,vllm,yes,acc,none,0.6581818181818182,0.02003194252384729,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 +v2anneal_120k,include_base_44_spanish_arts_humanities,0,lm-eval,vllm,,acc,none,0.58,0.03127799950463661,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 +v2anneal_120k,include_base_44_spanish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 +v2anneal_120k,include_base_44_spanish_social_science,0,lm-eval,vllm,,acc,none,0.732,0.02806876238252672,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 +v2anneal_120k,include_base_44_spanish_stem,0,lm-eval,vllm,,acc,none,0.76,0.08717797887081347,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550a2d1aba_2026-09-30T08-32-50.090240.json,1790757010.7558863,1 +v2anneal_120k,include_base_44_turkish,0,lm-eval,vllm,yes,acc,none,0.5638686131386861,0.020729270503815,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 +v2anneal_120k,include_base_44_turkish_arts_humanities,0,lm-eval,vllm,,acc,none,0.536144578313253,0.038823108508905954,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 +v2anneal_120k,include_base_44_turkish_business_commerce,0,lm-eval,vllm,,acc,none,0.7108433734939759,0.035294868015111204,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 +v2anneal_120k,include_base_44_turkish_social_science,0,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 +v2anneal_120k,include_base_44_turkish_stem,0,lm-eval,vllm,,acc,none,0.34,0.0676726816132972,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78998f6ed0_2026-09-30T08-39-02.736261.json,1790757382.7415192,1 +v2anneal_120k,include_base_44_ukrainian,0,lm-eval,vllm,yes,acc,none,0.6218181818181818,0.02072253123168508,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5949bfffcb_2026-09-30T08-26-13.105199.json,1790756610.9756362,1 +v2anneal_120k,include_base_44_ukrainian_arts_humanities,0,lm-eval,vllm,,acc,none,0.616,0.030821679117375447,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5949bfffcb_2026-09-30T08-26-13.105199.json,1790756610.9756362,1 +v2anneal_120k,include_base_44_ukrainian_social_science,0,lm-eval,vllm,,acc,none,0.636,0.030491555220405475,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5949bfffcb_2026-09-30T08-26-13.105199.json,1790756610.9756362,1 +v2anneal_120k,include_base_44_ukrainian_stem,0,lm-eval,vllm,,acc,none,0.58,0.07050835816716038,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5949bfffcb_2026-09-30T08-26-13.105199.json,1790756610.9756362,1 +v2anneal_120k,jeopardy,10,lm-eval,vllm,,exact_match,strict-match,0.5356636750118091,0.010841880009403592,2117,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b91c0afada_2026-09-30T08-49-37.261937.json,1790757989.3484197,1 +v2anneal_120k,lambada_openai,0,lm-eval,vllm,,acc,none,0.7339413933630895,0.006156465073667463,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c24cdf9273_2026-09-30T08-43-51.938741.json,1790757643.8164952,1 +v2anneal_120k,lambada_openai,0,lm-eval,vllm,,perplexity,none,3.523157791936209,0.06998351715598007,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c24cdf9273_2026-09-30T08-43-51.938741.json,1790757643.8164952,1 +v2anneal_120k,mbpp,3,lm-eval,vllm,,pass_at_1,none,0.622,0.021706550824518184,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/48966cbd64_2026-09-30T08-34-54.493731.json,1790756981.0990462,1 +v2anneal_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.704,0.02892893938837963,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/214d19c231_2026-09-30T08-11-25.206951.json,1790754230.0976589,1 +v2anneal_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,strict-match,0.732,0.02806876238252669,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/214d19c231_2026-09-30T08-11-25.206951.json,1790754230.0976589,1 +v2anneal_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.848,0.022752024491765464,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/23c1d97ca1_2026-09-30T07-40-38.393294.json,1790753866.7507765,1 +v2anneal_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,strict-match,0.788,0.025901884690541166,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/23c1d97ca1_2026-09-30T07-40-38.393294.json,1790753866.7507765,1 +v2anneal_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.828,0.023915513944486218,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/58bda3757f_2026-09-30T07-38-58.499451.json,1790753752.2450347,1 +v2anneal_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,strict-match,0.756,0.02721799546455318,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/58bda3757f_2026-09-30T07-38-58.499451.json,1790753752.2450347,1 +v2anneal_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.684,0.02946265759857868,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/cf19d7ef9a_2026-09-30T08-39-25.252625.json,1790757384.1331484,1 +v2anneal_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,strict-match,0.736,0.02793451895769091,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/cf19d7ef9a_2026-09-30T08-39-25.252625.json,1790757384.1331484,1 +v2anneal_120k,mmlu,5,lm-eval,vllm,yes,acc,none,0.7277453354223045,0.0035974184871722203,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_abstract_algebra,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_anatomy,5,lm-eval,vllm,,acc,none,0.6222222222222222,0.041883075375958506,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_business_ethics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7509433962264151,0.02661648298050167,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_college_biology,5,lm-eval,vllm,,acc,none,0.8611111111111112,0.028919802956134912,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_college_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_college_mathematics,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_college_medicine,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.03414014007044037,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_computer_security,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7872340425531915,0.02675439134803978,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_econometrics,5,lm-eval,vllm,,acc,none,0.5964912280701754,0.04615186962583705,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7310344827586207,0.03695183311650232,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6481481481481481,0.024594975128920938,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_formal_logic,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.04285714285714286,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_global_facts,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_biology,5,lm-eval,vllm,,acc,none,0.8709677419354839,0.01907088925479277,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6798029556650246,0.032826493853041455,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8424242424242424,0.02845038880528439,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_geography,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.02239078763821682,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9637305699481865,0.013492659751295115,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7897435897435897,0.020660597485026883,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5148148148148148,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8865546218487395,0.020600225750204797,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_physics,5,lm-eval,vllm,,acc,none,0.5629139072847682,0.040500357222306375,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_psychology,5,lm-eval,vllm,,acc,none,0.9100917431192661,0.012264304540230489,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6851851851851852,0.03167468706828983,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8676470588235294,0.02378429752091887,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8818565400843882,0.021011052659878477,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_human_aging,5,lm-eval,vllm,,acc,none,0.7623318385650224,0.02856807946471428,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_human_sexuality,5,lm-eval,vllm,,acc,none,0.8320610687022901,0.0327854853734314,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_humanities,5,lm-eval,vllm,yes,acc,none,0.6814027630180659,0.006513620090495235,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_jurisprudence,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.03602814176392641,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7975460122699386,0.031570650789119054,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_machine_learning,5,lm-eval,vllm,,acc,none,0.625,0.04595091388086298,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_management,5,lm-eval,vllm,,acc,none,0.8349514563106796,0.03675668832233187,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_marketing,5,lm-eval,vllm,,acc,none,0.8974358974358975,0.01987565502786746,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_medical_genetics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_miscellaneous,5,lm-eval,vllm,,acc,none,0.8378033205619413,0.01318222261672081,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_moral_disputes,5,lm-eval,vllm,,acc,none,0.7947976878612717,0.021742519835276364,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5418994413407822,0.016663683295020503,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_nutrition,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.024848018263875137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_other,5,lm-eval,vllm,yes,acc,none,0.7444480205986482,0.0075766412475204575,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_philosophy,5,lm-eval,vllm,,acc,none,0.752411575562701,0.024513879973621984,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_prehistory,5,lm-eval,vllm,,acc,none,0.8395061728395061,0.02042395535477805,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_professional_accounting,5,lm-eval,vllm,,acc,none,0.5390070921985816,0.029736592526424455,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_professional_law,5,lm-eval,vllm,,acc,none,0.5664928292046936,0.012656810383983882,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_professional_medicine,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.026799562024887664,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_professional_psychology,5,lm-eval,vllm,,acc,none,0.75,0.01751781884501444,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_public_relations,5,lm-eval,vllm,,acc,none,0.7181818181818181,0.043091187099464606,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8277543061423465,0.00665014813921035,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_sociology,5,lm-eval,vllm,,acc,none,0.8706467661691543,0.02372983088101855,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_stem,5,lm-eval,vllm,yes,acc,none,0.6828417380272757,0.008021755838114007,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_virology,5,lm-eval,vllm,,acc,none,0.5481927710843374,0.0387437155658795,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,mmlu_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/16fcc092f3_2026-09-30T08-19-58.126733.json,1790756044.5307932,1 +v2anneal_120k,multiblimp_bul,0,lm-eval,vllm,,acc,none,0.984947111472742,0.0024564832092906753,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fd93079d3e_2026-09-30T08-32-56.851583.json,1790757012.2006617,1 +v2anneal_120k,multiblimp_bul,0,lm-eval,vllm,,acc_norm,none,0.9772172497965825,0.0030102048992459093,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fd93079d3e_2026-09-30T08-32-56.851583.json,1790757012.2006617,1 +v2anneal_120k,multiblimp_cat,0,lm-eval,vllm,,acc,none,0.9772329246935202,0.0031217614380178514,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/29d71a90c9_2026-09-30T08-47-42.729319.json,1790757887.8651025,1 +v2anneal_120k,multiblimp_cat,0,lm-eval,vllm,,acc_norm,none,0.9776707530647986,0.0030922912692911255,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/29d71a90c9_2026-09-30T08-47-42.729319.json,1790757887.8651025,1 +v2anneal_120k,multiblimp_ces,0,lm-eval,vllm,,acc,none,0.9518327067669173,0.0032825144805596292,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2437361283_2026-09-30T08-52-49.665259.json,1790758109.0033753,1 +v2anneal_120k,multiblimp_ces,0,lm-eval,vllm,,acc_norm,none,0.9541823308270677,0.0032054012276831923,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2437361283_2026-09-30T08-52-49.665259.json,1790758109.0033753,1 +v2anneal_120k,multiblimp_dan,0,lm-eval,vllm,,acc,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95ba6406d1_2026-09-30T08-35-57.676389.json,1790757134.6447525,1 +v2anneal_120k,multiblimp_dan,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/95ba6406d1_2026-09-30T08-35-57.676389.json,1790757134.6447525,1 +v2anneal_120k,multiblimp_deu,0,lm-eval,vllm,,acc,none,0.9873803307223673,0.0023290870729458513,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e1650c6000_2026-09-30T08-31-30.409241.json,1790756929.1146824,1 +v2anneal_120k,multiblimp_deu,0,lm-eval,vllm,,acc_norm,none,0.9852045256744996,0.002519110092348522,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e1650c6000_2026-09-30T08-31-30.409241.json,1790756929.1146824,1 +v2anneal_120k,multiblimp_ell,0,lm-eval,vllm,,acc,none,0.9945255474452555,0.0022298274651133573,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e59f0e973b_2026-09-30T07-40-29.956193.json,1790753865.2941065,1 +v2anneal_120k,multiblimp_ell,0,lm-eval,vllm,,acc_norm,none,0.9981751824817519,0.0012897515102687142,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e59f0e973b_2026-09-30T07-40-29.956193.json,1790753865.2941065,1 +v2anneal_120k,multiblimp_eng,0,lm-eval,vllm,,acc,none,0.9935064935064936,0.002896421914185563,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9e55c73926_2026-09-30T08-43-09.228610.json,1790757644.6146133,1 +v2anneal_120k,multiblimp_eng,0,lm-eval,vllm,,acc_norm,none,0.9883116883116884,0.0038757850932000515,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9e55c73926_2026-09-30T08-43-09.228610.json,1790757644.6146133,1 +v2anneal_120k,multiblimp_est,0,lm-eval,vllm,,acc,none,0.9044660194174757,0.0057938973043891746,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/83546e4990_2026-09-30T07-34-35.973067.json,1790753499.5758636,1 +v2anneal_120k,multiblimp_est,0,lm-eval,vllm,,acc_norm,none,0.9009708737864077,0.005887522474827137,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/83546e4990_2026-09-30T07-34-35.973067.json,1790753499.5758636,1 +v2anneal_120k,multiblimp_eus,0,lm-eval,vllm,,acc,none,0.9487179487179487,0.0133741688167181,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/924c69e5f9_2026-09-30T08-38-46.315998.json,1790757382.793441,1 +v2anneal_120k,multiblimp_eus,0,lm-eval,vllm,,acc_norm,none,0.6227106227106227,0.029389755560222004,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/924c69e5f9_2026-09-30T08-38-46.315998.json,1790757382.793441,1 +v2anneal_120k,multiblimp_fin,0,lm-eval,vllm,,acc,none,0.9389105058365759,0.004725125105853984,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/baf1cdb786_2026-09-30T08-11-16.663762.json,1790754230.6025035,1 +v2anneal_120k,multiblimp_fin,0,lm-eval,vllm,,acc_norm,none,0.932295719844358,0.004956816657465678,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/baf1cdb786_2026-09-30T08-11-16.663762.json,1790754230.6025035,1 +v2anneal_120k,multiblimp_fra,0,lm-eval,vllm,,acc,none,0.9913657770800628,0.0018332180191281344,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7780230490_2026-09-30T07-44-50.054559.json,1790754121.1507268,1 +v2anneal_120k,multiblimp_fra,0,lm-eval,vllm,,acc_norm,none,0.9862637362637363,0.0023063030340050696,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7780230490_2026-09-30T07-44-50.054559.json,1790754121.1507268,1 +v2anneal_120k,multiblimp_gle,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.06734350297014738,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9ee5047ae8_2026-09-30T07-34-20.477366.json,1790753513.6247275,1 +v2anneal_120k,multiblimp_gle,0,lm-eval,vllm,,acc_norm,none,0.75,0.08333333333333333,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9ee5047ae8_2026-09-30T07-34-20.477366.json,1790753513.6247275,1 +v2anneal_120k,multiblimp_glg,0,lm-eval,vllm,,acc,none,0.9681274900398407,0.006405683674396879,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/705c91b2a9_2026-09-30T08-21-01.990554.json,1790756304.2746775,1 +v2anneal_120k,multiblimp_glg,0,lm-eval,vllm,,acc_norm,none,0.952191235059761,0.007780489692849838,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/705c91b2a9_2026-09-30T08-21-01.990554.json,1790756304.2746775,1 +v2anneal_120k,multiblimp_hbs,0,lm-eval,vllm,,acc,none,0.9768715763846622,0.0026225517472673564,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e5256329a7_2026-09-30T08-43-31.324693.json,1790757623.6114643,1 +v2anneal_120k,multiblimp_hbs,0,lm-eval,vllm,,acc_norm,none,0.9765672550213025,0.00263933778428641,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e5256329a7_2026-09-30T08-43-31.324693.json,1790757623.6114643,1 +v2anneal_120k,multiblimp_hun,0,lm-eval,vllm,,acc,none,0.9810650887573964,0.004691474113624961,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a83b7d0e38_2026-09-30T08-20-25.207801.json,1790756205.1350284,1 +v2anneal_120k,multiblimp_hun,0,lm-eval,vllm,,acc_norm,none,0.9798816568047337,0.004832943264222541,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a83b7d0e38_2026-09-30T08-20-25.207801.json,1790756205.1350284,1 +v2anneal_120k,multiblimp_isl,0,lm-eval,vllm,,acc,none,0.9696536951088897,0.0032417701662697277,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0ea4a5db28_2026-09-30T08-14-24.739510.json,1790755830.2465158,1 +v2anneal_120k,multiblimp_isl,0,lm-eval,vllm,,acc_norm,none,0.9625133880756872,0.0035897356573365,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0ea4a5db28_2026-09-30T08-14-24.739510.json,1790755830.2465158,1 +v2anneal_120k,multiblimp_ita,0,lm-eval,vllm,,acc,none,0.9619873291097032,0.0034924729766106738,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0dd099535_2026-09-30T08-23-03.181288.json,1790756405.6435413,1 +v2anneal_120k,multiblimp_ita,0,lm-eval,vllm,,acc_norm,none,0.9539846615538513,0.0038265394236287995,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0dd099535_2026-09-30T08-23-03.181288.json,1790756405.6435413,1 +v2anneal_120k,multiblimp_kat,0,lm-eval,vllm,,acc,none,0.9558823529411765,0.014413198705704818,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/81cc5995ca_2026-09-30T08-31-41.707415.json,1790756930.2532284,1 +v2anneal_120k,multiblimp_kat,0,lm-eval,vllm,,acc_norm,none,0.9117647058823529,0.01990739979131697,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/81cc5995ca_2026-09-30T08-31-41.707415.json,1790756930.2532284,1 +v2anneal_120k,multiblimp_lav,0,lm-eval,vllm,,acc,none,0.9604221635883905,0.0035413116097079414,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c29251978_2026-09-30T08-33-19.491316.json,1790757005.622636,1 +v2anneal_120k,multiblimp_lav,0,lm-eval,vllm,,acc_norm,none,0.9564643799472295,0.0037064982500016564,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1c29251978_2026-09-30T08-33-19.491316.json,1790757005.622636,1 +v2anneal_120k,multiblimp_lit,0,lm-eval,vllm,,acc,none,0.9813559322033898,0.003939369428601548,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/180842076e_2026-09-30T08-11-03.581154.json,1790754229.9082053,1 +v2anneal_120k,multiblimp_lit,0,lm-eval,vllm,,acc_norm,none,0.9805084745762712,0.004026166098461977,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/180842076e_2026-09-30T08-11-03.581154.json,1790754229.9082053,1 +v2anneal_120k,multiblimp_mkd,0,lm-eval,vllm,,acc,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/38e1622f9b_2026-09-30T08-31-18.349890.json,1790756931.1874237,1 +v2anneal_120k,multiblimp_mkd,0,lm-eval,vllm,,acc_norm,none,0.9230769230769231,0.043227037457616635,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/38e1622f9b_2026-09-30T08-31-18.349890.json,1790756931.1874237,1 +v2anneal_120k,multiblimp_nld,0,lm-eval,vllm,,acc,none,0.9515229515229515,0.004449382666732822,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4976faba87_2026-09-30T08-39-06.135503.json,1790757372.8123157,1 +v2anneal_120k,multiblimp_nld,0,lm-eval,vllm,,acc_norm,none,0.924924924924925,0.00545912663303515,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4976faba87_2026-09-30T08-39-06.135503.json,1790757372.8123157,1 +v2anneal_120k,multiblimp_pol,0,lm-eval,vllm,,acc,none,0.9584352078239609,0.003489827126709908,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3eb43b31ad_2026-09-30T08-31-41.030189.json,1790756931.2251399,1 +v2anneal_120k,multiblimp_pol,0,lm-eval,vllm,,acc_norm,none,0.9391809290953546,0.004178825645109273,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3eb43b31ad_2026-09-30T08-31-41.030189.json,1790756931.2251399,1 +v2anneal_120k,multiblimp_por,0,lm-eval,vllm,,acc,none,0.9724409448818898,0.0029657022925976134,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1502915446_2026-09-30T08-20-42.648171.json,1790756204.654618,1 +v2anneal_120k,multiblimp_por,0,lm-eval,vllm,,acc_norm,none,0.9698162729658792,0.003099523537944906,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1502915446_2026-09-30T08-20-42.648171.json,1790756204.654618,1 +v2anneal_120k,multiblimp_ron,0,lm-eval,vllm,,acc,none,0.9630350194552529,0.004162079465649507,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/56523d5db9_2026-09-30T08-37-23.814875.json,1790757280.8378541,1 +v2anneal_120k,multiblimp_ron,0,lm-eval,vllm,,acc_norm,none,0.958171206225681,0.004416246591731525,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/56523d5db9_2026-09-30T08-37-23.814875.json,1790757280.8378541,1 +v2anneal_120k,multiblimp_slk,0,lm-eval,vllm,,acc,none,0.9437876960193003,0.003578021742558625,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c8ceea0aa4_2026-09-30T08-14-25.156563.json,1790755617.9412036,1 +v2anneal_120k,multiblimp_slk,0,lm-eval,vllm,,acc_norm,none,0.944270205066345,0.0035635429073718815,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c8ceea0aa4_2026-09-30T08-14-25.156563.json,1790755617.9412036,1 +v2anneal_120k,multiblimp_slv,0,lm-eval,vllm,,acc,none,0.9326343966094134,0.0037440262956893364,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fe42d4d144_2026-09-30T07-34-53.986753.json,1790753469.5036514,1 +v2anneal_120k,multiblimp_slv,0,lm-eval,vllm,,acc_norm,none,0.9223734106625028,0.003996894766503557,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fe42d4d144_2026-09-30T07-34-53.986753.json,1790753469.5036514,1 +v2anneal_120k,multiblimp_spa,0,lm-eval,vllm,,acc,none,0.9822904368358913,0.0026170198938226304,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8b08e09b56_2026-09-30T07-38-45.004933.json,1790753750.671699,1 +v2anneal_120k,multiblimp_spa,0,lm-eval,vllm,,acc_norm,none,0.983077528532074,0.0025592276630338104,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8b08e09b56_2026-09-30T07-38-45.004933.json,1790753750.671699,1 +v2anneal_120k,multiblimp_sqi,0,lm-eval,vllm,,acc,none,0.9465020576131687,0.01446510656878504,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/762fbe30a8_2026-09-30T07-38-12.286719.json,1790753749.6544251,1 +v2anneal_120k,multiblimp_sqi,0,lm-eval,vllm,,acc_norm,none,0.9012345679012346,0.019178459585449004,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/762fbe30a8_2026-09-30T07-38-12.286719.json,1790753749.6544251,1 +v2anneal_120k,multiblimp_swe,0,lm-eval,vllm,,acc,none,0.9950248756218906,0.004975124378109453,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/be61369270_2026-09-30T08-26-46.052029.json,1790756651.2086518,1 +v2anneal_120k,multiblimp_swe,0,lm-eval,vllm,,acc_norm,none,0.9900497512437811,0.007018276606798947,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/be61369270_2026-09-30T08-26-46.052029.json,1790756651.2086518,1 +v2anneal_120k,multiblimp_tur,0,lm-eval,vllm,,acc,none,0.9064293915040184,0.0069797092363050525,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ea946abb1b_2026-09-30T08-26-10.397916.json,1790756611.6366866,1 +v2anneal_120k,multiblimp_tur,0,lm-eval,vllm,,acc_norm,none,0.8461538461538461,0.008647062590129767,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ea946abb1b_2026-09-30T08-26-10.397916.json,1790756611.6366866,1 +v2anneal_120k,multiblimp_ukr,0,lm-eval,vllm,,acc,none,0.9795918367346939,0.0026996759326348425,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd398eb3a2_2026-09-30T08-45-26.360584.json,1790757750.4302871,1 +v2anneal_120k,multiblimp_ukr,0,lm-eval,vllm,,acc_norm,none,0.9719387755102041,0.0031532605656132426,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/bd398eb3a2_2026-09-30T08-45-26.360584.json,1790757750.4302871,1 +v2anneal_120k,openbookqa,0,lm-eval,vllm,,acc,none,0.348,0.021323728632807425,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cdb44fab1_2026-09-30T08-37-25.800861.json,1790757281.0389993,1 +v2anneal_120k,openbookqa,0,lm-eval,vllm,,acc_norm,none,0.446,0.022252153078595936,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8cdb44fab1_2026-09-30T08-37-25.800861.json,1790757281.0389993,1 +v2anneal_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,bleu,none,15.003650618866999,0.2640478125195402,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/254d53288f_2026-09-30T08-53-07.176457.json,1790758110.3719418,1 +v2anneal_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,chrf,none,33.51244895183558,0.30424075494002356,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/254d53288f_2026-09-30T08-53-07.176457.json,1790758110.3719418,1 +v2anneal_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,bleu,none,24.287465757521666,0.2767299568481002,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/243dd202fa_2026-09-30T08-33-29.472801.json,1790756930.1446486,1 +v2anneal_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,chrf,none,42.93742966081114,0.2513793268225009,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/243dd202fa_2026-09-30T08-33-29.472801.json,1790756930.1446486,1 +v2anneal_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,bleu,none,29.978766998472672,0.33278654183215584,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0f14ca7da4_2026-09-30T08-45-26.712738.json,1790757646.391393,1 +v2anneal_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,chrf,none,49.13262126141007,0.27072821166642186,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0f14ca7da4_2026-09-30T08-45-26.712738.json,1790757646.391393,1 +v2anneal_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,bleu,none,26.533052554215498,0.31660376659960104,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/52f4aeb8b0_2026-09-30T16-53-06.329376.json,1790786894.1423683,1 +v2anneal_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,chrf,none,46.47287400648327,0.28401287229377115,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/52f4aeb8b0_2026-09-30T16-53-06.329376.json,1790786894.1423683,1 +v2anneal_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,bleu,none,28.53342457274273,0.35851197786269856,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7824c3562d_2026-09-30T08-40-52.607785.json,1790757372.7801106,1 +v2anneal_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,chrf,none,46.94123205165745,0.3223752216868438,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7824c3562d_2026-09-30T08-40-52.607785.json,1790757372.7801106,1 +v2anneal_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,bleu,none,12.06991503307192,0.2566605620445614,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1560b8ce00_2026-09-30T08-16-52.301574.json,1790755924.9914212,1 +v2anneal_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,chrf,none,36.26491350440361,0.3230513608892678,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1560b8ce00_2026-09-30T08-16-52.301574.json,1790755924.9914212,1 +v2anneal_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,bleu,none,17.73760258494243,0.2890172152738235,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/de5685eb7e_2026-09-30T08-55-16.893905.json,1790758233.8252575,1 +v2anneal_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,chrf,none,40.40293124431965,0.2426036934530269,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/de5685eb7e_2026-09-30T08-55-16.893905.json,1790758233.8252575,1 +v2anneal_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,bleu,none,29.46689780485439,0.3178939458562562,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f58a23c313_2026-09-30T08-28-14.275106.json,1790756609.707454,1 +v2anneal_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,chrf,none,51.45074381089818,0.25198153861091005,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f58a23c313_2026-09-30T08-28-14.275106.json,1790756609.707454,1 +v2anneal_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,bleu,none,22.58397892805329,0.33834839392266836,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/164798c773_2026-09-30T08-25-11.985623.json,1790756403.3089743,1 +v2anneal_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,chrf,none,47.30599141902181,0.3113692661003813,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/164798c773_2026-09-30T08-25-11.985623.json,1790756403.3089743,1 +v2anneal_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,bleu,none,21.889178171188618,0.33952033480092003,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b15951784b_2026-09-30T07-42-59.228838.json,1790753865.981722,1 +v2anneal_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,chrf,none,43.44546833425687,0.3160119427452474,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b15951784b_2026-09-30T07-42-59.228838.json,1790753865.981722,1 +v2anneal_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,bleu,none,28.385013188787394,0.3706904651286205,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7f7b8db687_2026-09-30T08-45-09.388305.json,1790757622.0427928,1 +v2anneal_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,chrf,none,50.03014751103492,0.33848535604583513,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7f7b8db687_2026-09-30T08-45-09.388305.json,1790757622.0427928,1 +v2anneal_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,bleu,none,21.705449936407522,0.3476460560068148,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6289986c3_2026-09-30T08-28-29.250542.json,1790756611.5832756,1 +v2anneal_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,chrf,none,45.35800754478377,0.2597731358802138,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6289986c3_2026-09-30T08-28-29.250542.json,1790756611.5832756,1 +v2anneal_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,bleu,none,16.77894598071746,0.3369373356404649,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e026493e54_2026-09-30T08-40-53.271183.json,1790757372.8209233,1 +v2anneal_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,chrf,none,45.845114301587806,0.2476938621269921,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e026493e54_2026-09-30T08-40-53.271183.json,1790757372.8209233,1 +v2anneal_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,bleu,none,15.64501725950506,0.2347428809936428,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/15f15bb785_2026-09-30T08-51-30.861043.json,1790757990.28161,1 +v2anneal_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,chrf,none,41.8703322995393,0.27165318914016173,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/15f15bb785_2026-09-30T08-51-30.861043.json,1790757990.28161,1 +v2anneal_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,bleu,none,25.59032748310354,0.31229139405300194,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0f4f4a4f11_2026-09-30T08-34-55.105435.json,1790757010.440211,1 +v2anneal_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,chrf,none,53.01937756038305,0.2561923271366798,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0f4f4a4f11_2026-09-30T08-34-55.105435.json,1790757010.440211,1 +v2anneal_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,bleu,none,17.061013299325463,0.27042527602165894,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f21f3f4129_2026-09-30T07-36-41.935735.json,1790753513.6043768,1 +v2anneal_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,chrf,none,40.29816848135213,0.2411277445556396,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f21f3f4129_2026-09-30T07-36-41.935735.json,1790753513.6043768,1 +v2anneal_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,bleu,none,27.867270653374906,0.36381265112931677,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d3cb1b10d0_2026-09-30T08-23-11.799042.json,1790756302.5977905,1 +v2anneal_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,chrf,none,50.22688626715382,0.2841581782125067,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d3cb1b10d0_2026-09-30T08-23-11.799042.json,1790756302.5977905,1 +v2anneal_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,bleu,none,18.525758021609157,0.289716197800278,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f57f2cf6ad_2026-09-30T07-36-50.295715.json,1790753513.7625396,1 +v2anneal_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,chrf,none,43.03170468479124,0.2339174077703083,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f57f2cf6ad_2026-09-30T07-36-50.295715.json,1790753513.7625396,1 +v2anneal_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,bleu,none,21.290054084799436,0.3290764099697444,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0524013ad0_2026-09-30T08-51-25.359351.json,1790757989.5639303,1 +v2anneal_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,chrf,none,44.92578462272227,0.24275415950233947,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0524013ad0_2026-09-30T08-51-25.359351.json,1790757989.5639303,1 +v2anneal_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,bleu,none,20.145734697908825,0.280501878341418,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac7843847e_2026-09-30T08-28-24.312806.json,1790756611.0908015,1 +v2anneal_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,chrf,none,46.2020415806725,0.2296496794525854,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ac7843847e_2026-09-30T08-28-24.312806.json,1790756611.0908015,1 +v2anneal_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,bleu,none,30.855543527173815,0.3083742476762461,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4096fbae59_2026-09-30T08-44-34.229123.json,1790757572.4025536,1 +v2anneal_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,chrf,none,54.28100232910595,0.2884988778566187,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4096fbae59_2026-09-30T08-44-34.229123.json,1790757572.4025536,1 +v2anneal_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,bleu,none,20.995299381934533,0.3524491906204629,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b650c29367_2026-09-30T08-45-50.758022.json,1790757646.438095,1 +v2anneal_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,chrf,none,45.893538079574135,0.28110560471292106,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b650c29367_2026-09-30T08-45-50.758022.json,1790757646.438095,1 +v2anneal_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,bleu,none,24.58250681034448,0.29862282018317043,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/01e90882e0_2026-09-30T08-39-40.808204.json,1790757279.7737458,1 +v2anneal_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,chrf,none,50.71973943924048,0.2603471087477354,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/01e90882e0_2026-09-30T08-39-40.808204.json,1790757279.7737458,1 +v2anneal_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,bleu,none,25.76001460058189,0.3925544122927604,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c38fdc963e_2026-09-30T08-24-58.577260.json,1790756401.6354928,1 +v2anneal_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,chrf,none,49.840842672049426,0.30549879066607116,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c38fdc963e_2026-09-30T08-24-58.577260.json,1790756401.6354928,1 +v2anneal_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,bleu,none,24.780025615180204,0.3565446556945002,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b400e8993e_2026-09-30T08-15-21.595163.json,1790755617.97272,1 +v2anneal_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,chrf,none,47.07280552178489,0.2510125642597503,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b400e8993e_2026-09-30T08-15-21.595163.json,1790755617.97272,1 +v2anneal_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,bleu,none,15.919063244134337,0.2692026366641734,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4625dddc43_2026-09-30T08-45-28.142244.json,1790757643.9533594,1 +v2anneal_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,chrf,none,42.178713341078435,0.257317283215899,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4625dddc43_2026-09-30T08-45-28.142244.json,1790757643.9533594,1 +v2anneal_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,bleu,none,19.783467403594074,0.3495074887116293,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b932b9c997_2026-09-30T16-53-11.805213.json,1790786902.5669606,1 +v2anneal_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,chrf,none,39.914268318330095,0.4614420792498697,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b932b9c997_2026-09-30T16-53-11.805213.json,1790786902.5669606,1 +v2anneal_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,bleu,none,33.03433486457814,0.3456247721252961,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/184aa56f36_2026-09-30T08-15-26.763597.json,1790755617.9424443,1 +v2anneal_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,chrf,none,53.24908306073861,0.31492520088834447,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/184aa56f36_2026-09-30T08-15-26.763597.json,1790755617.9424443,1 +v2anneal_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,bleu,none,20.68107561104388,0.35915687539291524,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1b5e77e39b_2026-09-30T08-39-40.789987.json,1790757281.2179785,1 +v2anneal_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,chrf,none,48.64754938596812,0.29605691206317286,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1b5e77e39b_2026-09-30T08-39-40.789987.json,1790757281.2179785,1 +v2anneal_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,bleu,none,16.705421272378242,0.2633416845167624,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/037cf1f3e3_2026-09-30T07-36-26.059552.json,1790753469.2214413,1 +v2anneal_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,chrf,none,38.26208638576516,0.25301480909423996,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/037cf1f3e3_2026-09-30T07-36-26.059552.json,1790753469.2214413,1 +v2anneal_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,bleu,none,29.421452431470037,0.32458241325941467,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/339108969b_2026-09-30T08-20-20.508829.json,1790756125.8833287,1 +v2anneal_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,chrf,none,47.781699805853194,0.31836642040344765,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/339108969b_2026-09-30T08-20-20.508829.json,1790756125.8833287,1 +v2anneal_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,bleu,none,28.061321049800746,0.3417258778656989,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2cbb54ed6e_2026-09-30T08-21-29.233441.json,1790756204.8603153,1 +v2anneal_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,chrf,none,46.802765071196426,0.2728225863730105,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2cbb54ed6e_2026-09-30T08-21-29.233441.json,1790756204.8603153,1 +v2anneal_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,bleu,none,23.14526492362293,0.31722385658429425,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/aa6cb573d5_2026-09-30T08-50-57.999335.json,1790757959.9055662,1 +v2anneal_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,chrf,none,42.890376018543556,0.2603689928410946,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/aa6cb573d5_2026-09-30T08-50-57.999335.json,1790757959.9055662,1 +v2anneal_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,bleu,none,16.997531847170016,0.2555695170525282,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c1836b0768_2026-09-30T08-33-24.141971.json,1790756929.4831698,1 +v2anneal_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,chrf,none,35.01414914469773,0.28821738525247687,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c1836b0768_2026-09-30T08-33-24.141971.json,1790756929.4831698,1 +v2anneal_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,bleu,none,29.856998549113236,0.3913527154196685,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0d927ed6a6_2026-09-30T08-06-50.709866.json,1790754113.534177,1 +v2anneal_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,chrf,none,49.34814681616648,0.3248485770785364,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0d927ed6a6_2026-09-30T08-06-50.709866.json,1790754113.534177,1 +v2anneal_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,bleu,none,22.50774023429512,0.2868998352674406,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/360a5d2ae7_2026-09-30T16-53-06.317467.json,1790786894.1421666,1 +v2anneal_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,chrf,none,41.06392598464278,0.23666832130981091,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/360a5d2ae7_2026-09-30T16-53-06.317467.json,1790786894.1421666,1 +v2anneal_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,bleu,none,29.64830520634905,0.3253963591089322,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26d94f2743_2026-09-30T07-40-35.308510.json,1790753750.9416914,1 +v2anneal_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,chrf,none,47.28039758188727,0.2940858179971653,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/26d94f2743_2026-09-30T07-40-35.308510.json,1790753750.9416914,1 +v2anneal_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,bleu,none,26.247786498125055,0.3551103835349797,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3050f2a1e_2026-09-30T08-15-21.379186.json,1790755617.8509512,1 +v2anneal_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,chrf,none,44.16699374920105,0.2732754115438893,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b3050f2a1e_2026-09-30T08-15-21.379186.json,1790755617.8509512,1 +v2anneal_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,bleu,none,27.186913764167596,0.32908472060838384,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d0ef94c0c9_2026-09-30T08-35-09.533611.json,1790757011.3854713,1 +v2anneal_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,chrf,none,45.67520805121994,0.2783786339310545,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d0ef94c0c9_2026-09-30T08-35-09.533611.json,1790757011.3854713,1 +v2anneal_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,bleu,none,22.74723511435326,0.27378377269472687,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/978368894d_2026-09-30T08-21-34.587276.json,1790756204.313334,1 +v2anneal_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,chrf,none,41.82982284299739,0.2359548048961488,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/978368894d_2026-09-30T08-21-34.587276.json,1790756204.313334,1 +v2anneal_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,bleu,none,31.384082143878654,0.2995990117103854,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/079b6bfc66_2026-09-30T08-40-55.381661.json,1790757372.8387737,1 +v2anneal_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,chrf,none,49.99679336635449,0.2523122123643974,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/079b6bfc66_2026-09-30T08-40-55.381661.json,1790757372.8387737,1 +v2anneal_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,bleu,none,26.257974285917662,0.32341369808266546,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/84e4b3f22f_2026-09-30T08-39-59.090663.json,1790757281.347818,1 +v2anneal_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,chrf,none,45.21653497053772,0.2753078119621563,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/84e4b3f22f_2026-09-30T08-39-59.090663.json,1790757281.347818,1 +v2anneal_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,bleu,none,29.954423622085674,0.3619846349487159,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/37fc80bb53_2026-09-30T07-42-25.354874.json,1790753864.9287243,1 +v2anneal_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,chrf,none,46.666919289096846,0.3537706498926314,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/37fc80bb53_2026-09-30T07-42-25.354874.json,1790753864.9287243,1 +v2anneal_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,bleu,none,31.215816623901514,0.3861614057450715,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1da297fd33_2026-09-30T07-36-21.050886.json,1790753469.3663568,1 +v2anneal_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,chrf,none,48.58454514033967,0.3235490481686245,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1da297fd33_2026-09-30T07-36-21.050886.json,1790753469.3663568,1 +v2anneal_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,bleu,none,31.52243061668225,0.3321225075204656,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/332f2059e8_2026-09-30T08-55-22.512505.json,1790758230.1469233,1 +v2anneal_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,chrf,none,49.26981564082949,0.2710033922723419,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/332f2059e8_2026-09-30T08-55-22.512505.json,1790758230.1469233,1 +v2anneal_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,bleu,none,20.764014890306164,0.2825665005463853,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0e0f89c84_2026-09-30T08-28-16.858677.json,1790756611.2532654,1 +v2anneal_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,chrf,none,40.37642265053128,0.2558400529702662,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c0e0f89c84_2026-09-30T08-28-16.858677.json,1790756611.2532654,1 +v2anneal_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,bleu,none,31.186399460110632,0.33669396333167223,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8a6cd1adc9_2026-09-30T08-13-16.929679.json,1790754225.6585321,1 +v2anneal_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,chrf,none,51.369319677751626,0.2565774608301896,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8a6cd1adc9_2026-09-30T08-13-16.929679.json,1790754225.6585321,1 +v2anneal_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,bleu,none,36.51785372638628,0.33933011267367824,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/54fc6b52fc_2026-09-30T08-24-48.520726.json,1790756405.5726144,1 +v2anneal_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,chrf,none,53.31416207375435,0.29360439008066735,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/54fc6b52fc_2026-09-30T08-24-48.520726.json,1790756405.5726144,1 +v2anneal_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,bleu,none,27.934500026684724,0.2803910451172384,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4181529a39_2026-09-30T07-40-41.524062.json,1790753750.4776633,1 +v2anneal_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,chrf,none,47.33245449153864,0.2550935392987942,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4181529a39_2026-09-30T07-40-41.524062.json,1790753750.4776633,1 +v2anneal_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,bleu,none,22.962690926896595,0.32151042833384175,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d137c03714_2026-09-30T08-50-38.714068.json,1790757958.284796,1 +v2anneal_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,chrf,none,41.54576871302295,0.28100575791765875,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d137c03714_2026-09-30T08-50-38.714068.json,1790757958.284796,1 +v2anneal_120k,piqa,0,lm-eval,vllm,,acc,none,0.8122959738846572,0.009110440292132566,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-21-10.381633.json,1790810334.1842988,1 +v2anneal_120k,piqa,0,lm-eval,vllm,,acc_norm,none,0.8193688792165397,0.00897597103733801,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-10-01-00-36-21/results/r_2026-09-30T23-21-10.381633.json,1790810334.1842988,1 +v2anneal_120k,piqa,10,lm-eval,vllm,,acc,none,0.8280739934711643,0.008803407033583992,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c8f538ebc7_2026-09-30T07-35-00.490064.json,1790753510.465127,1 +v2anneal_120k,piqa,10,lm-eval,vllm,,acc_norm,none,0.8373231773667029,0.008611024380872861,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c8f538ebc7_2026-09-30T07-35-00.490064.json,1790753510.465127,1 +v2anneal_120k,polymath_de_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f6f3e1f294_2026-09-30T08-27-18.486487.json,1790756652.4967537,1 +v2anneal_120k,polymath_de_low,0,lm-eval,vllm,,exact_match,none,0.448,0.04465783896075986,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/417254040e_2026-09-30T08-33-17.340591.json,1790757011.5856013,1 +v2anneal_120k,polymath_de_medium,0,lm-eval,vllm,,exact_match,none,0.048,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f7aada5b92_2026-09-30T07-34-52.021714.json,1790753498.2367218,1 +v2anneal_120k,polymath_de_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b0ba05a35e_2026-09-30T08-49-11.083958.json,1790757959.9288003,1 +v2anneal_120k,polymath_en_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9c34e0866f_2026-09-30T08-27-12.939236.json,1790756643.1978827,1 +v2anneal_120k,polymath_en_low,0,lm-eval,vllm,,exact_match,none,0.704,0.04099409870984186,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/89f59bfec9_2026-09-30T08-14-36.552167.json,1790755619.2151055,1 +v2anneal_120k,polymath_en_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/20abc30d97_2026-09-30T08-49-46.286521.json,1790757994.957994,1 +v2anneal_120k,polymath_en_top,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/56a52b4610_2026-09-30T08-27-02.418563.json,1790756644.905558,1 +v2anneal_120k,polymath_es_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d5df9ab151_2026-09-30T07-42-52.121431.json,1790753985.4851134,1 +v2anneal_120k,polymath_es_low,0,lm-eval,vllm,,exact_match,none,0.592,0.044134691204787364,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/282e5c3a18_2026-09-30T07-45-00.310238.json,1790754115.3406901,1 +v2anneal_120k,polymath_es_medium,0,lm-eval,vllm,,exact_match,none,0.048,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/a659b650e4_2026-09-30T07-39-01.057946.json,1790753750.7890701,1 +v2anneal_120k,polymath_es_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8642eb41b6_2026-09-30T08-43-31.800525.json,1790757621.8780978,1 +v2anneal_120k,polymath_fr_high,0,lm-eval,vllm,,exact_match,none,0.04,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/69bf33debd_2026-09-30T07-41-11.819919.json,1790753868.6236207,1 +v2anneal_120k,polymath_fr_low,0,lm-eval,vllm,,exact_match,none,0.552,0.04465783896075985,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/71a6972035_2026-09-30T07-40-50.964486.json,1790753868.0946627,1 +v2anneal_120k,polymath_fr_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/aa41cb4b61_2026-09-30T08-33-17.473013.json,1790757015.1166463,1 +v2anneal_120k,polymath_fr_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/58285c6fb5_2026-09-30T07-45-01.826734.json,1790754117.6309142,1 +v2anneal_120k,polymath_it_high,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/6c154cc864_2026-09-30T07-34-33.474585.json,1790753468.5649738,1 +v2anneal_120k,polymath_it_low,0,lm-eval,vllm,,exact_match,none,0.56,0.04457686366483793,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/9c3378aa3f_2026-09-30T08-20-55.457299.json,1790756204.2982337,1 +v2anneal_120k,polymath_it_medium,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5d04e90559_2026-09-30T07-45-14.113052.json,1790754117.8321943,1 +v2anneal_120k,polymath_it_top,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1df49e802d_2026-09-30T08-20-55.784192.json,1790756203.6029656,1 +v2anneal_120k,polymath_pt_high,0,lm-eval,vllm,,exact_match,none,0.04,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/299ae1443a_2026-09-30T08-27-10.164757.json,1790756650.7965853,1 +v2anneal_120k,polymath_pt_low,0,lm-eval,vllm,,exact_match,none,0.488,0.044888392062263534,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/2fdf24c8b0_2026-09-30T08-45-27.317003.json,1790757745.5037408,1 +v2anneal_120k,polymath_pt_medium,0,lm-eval,vllm,,exact_match,none,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/27685c5c3e_2026-09-30T08-26-40.343232.json,1790756610.888918,1 +v2anneal_120k,polymath_pt_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/08d5e9176e_2026-09-30T08-11-35.122166.json,1790754233.00453,1 +v2anneal_120k,sib200_als_Latn,0,lm-eval,vllm,,acc,none,0.27941176470588236,0.031493281045079584,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b38d397bad_2026-09-30T08-22-41.281427.json,1790756402.0516129,1 +v2anneal_120k,sib200_bos_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/84b0fb0940_2026-09-30T08-37-22.788656.json,1790757280.7902865,1 +v2anneal_120k,sib200_bul_Cyrl,0,lm-eval,vllm,,acc,none,0.4264705882352941,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/985293c9dd_2026-09-30T08-45-24.139562.json,1790757751.2152302,1 +v2anneal_120k,sib200_cat_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dd01a1f497_2026-09-30T08-49-11.320395.json,1790757994.1842062,1 +v2anneal_120k,sib200_ces_Latn,0,lm-eval,vllm,,acc,none,0.4019607843137255,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1022d1df8f_2026-09-30T07-44-37.987252.json,1790754113.7154791,1 +v2anneal_120k,sib200_dan_Latn,0,lm-eval,vllm,,acc,none,0.4166666666666667,0.03460228327239165,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/75ec6da525_2026-09-30T08-37-42.422062.json,1790757280.371878,1 +v2anneal_120k,sib200_deu_Latn,0,lm-eval,vllm,,acc,none,0.43137254901960786,0.034760990605016404,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7b90eeef8a_2026-09-30T08-22-48.020854.json,1790756406.4330118,1 +v2anneal_120k,sib200_ell_Grek,0,lm-eval,vllm,,acc,none,0.3382352941176471,0.03320574612945435,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/550d859acb_2026-09-30T08-20-31.373051.json,1790756203.6818733,1 +v2anneal_120k,sib200_eng_Latn,0,lm-eval,vllm,,acc,none,0.43137254901960786,0.034760990605016404,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/0659f8fd02_2026-09-30T08-32-51.994847.json,1790757008.9110518,1 +v2anneal_120k,sib200_est_Latn,0,lm-eval,vllm,,acc,none,0.38235294117647056,0.034107853389047135,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b467a6359f_2026-09-30T07-40-27.763149.json,1790753866.2138371,1 +v2anneal_120k,sib200_eus_Latn,0,lm-eval,vllm,,acc,none,0.3431372549019608,0.03332139944668079,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/4e119efeba_2026-09-30T08-27-13.816666.json,1790756651.6482928,1 +v2anneal_120k,sib200_fin_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d979fe0f9e_2026-09-30T08-16-32.632646.json,1790756032.0031965,1 +v2anneal_120k,sib200_fra_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dec5329e1c_2026-09-30T07-34-37.559672.json,1790753511.3087628,1 +v2anneal_120k,sib200_gle_Latn,0,lm-eval,vllm,,acc,none,0.4362745098039216,0.03480693138457044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/60a7c70837_2026-09-30T08-42-18.127640.json,1790757572.4251707,1 +v2anneal_120k,sib200_glg_Latn,0,lm-eval,vllm,,acc,none,0.4117647058823529,0.03454236585380609,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1901771811_2026-09-30T08-21-02.284495.json,1790756302.7182622,1 +v2anneal_120k,sib200_hrv_Latn,0,lm-eval,vllm,,acc,none,0.38235294117647056,0.034107853389047135,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/afd8167157_2026-09-30T08-14-14.634576.json,1790755619.037115,1 +v2anneal_120k,sib200_hun_Latn,0,lm-eval,vllm,,acc,none,0.3333333333333333,0.033086111132364336,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/fc4002c9d7_2026-09-30T08-52-51.406524.json,1790758208.7311106,1 +v2anneal_120k,sib200_isl_Latn,0,lm-eval,vllm,,acc,none,0.36764705882352944,0.0338413204567412,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/310da877a4_2026-09-30T08-38-51.226041.json,1790757372.4739983,1 +v2anneal_120k,sib200_ita_Latn,0,lm-eval,vllm,,acc,none,0.3284313725490196,0.03296245110172227,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f1b5f6c266_2026-09-30T08-38-57.051824.json,1790757376.0289724,1 +v2anneal_120k,sib200_kat_Geor,0,lm-eval,vllm,,acc,none,0.47549019607843135,0.035050931943487976,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e36f885401_2026-09-30T07-38-35.991544.json,1790753750.7517464,1 +v2anneal_120k,sib200_lit_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/452ca0845e_2026-09-30T08-22-45.376641.json,1790756401.2299142,1 +v2anneal_120k,sib200_lvs_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/05ff34b52f_2026-09-30T08-26-50.060445.json,1790756647.4421291,1 +v2anneal_120k,sib200_mkd_Cyrl,0,lm-eval,vllm,,acc,none,0.37254901960784315,0.03393388584958406,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/46d3c4fc72_2026-09-30T08-53-05.756592.json,1790758208.7756658,1 +v2anneal_120k,sib200_mlt_Latn,0,lm-eval,vllm,,acc,none,0.37254901960784315,0.03393388584958406,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f2907bd369_2026-09-30T07-40-29.392256.json,1790753866.0298214,1 +v2anneal_120k,sib200_nld_Latn,0,lm-eval,vllm,,acc,none,0.3627450980392157,0.0337449935631936,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/1a7451919c_2026-09-30T08-20-40.030608.json,1790756203.7966251,1 +v2anneal_120k,sib200_nob_Latn,0,lm-eval,vllm,,acc,none,0.35294117647058826,0.033540924375915215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/ed8bc71c08_2026-09-30T08-11-10.034827.json,1790754235.803487,1 +v2anneal_120k,sib200_pol_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b4906486d4_2026-09-30T07-40-50.037586.json,1790753866.62458,1 +v2anneal_120k,sib200_por_Latn,0,lm-eval,vllm,,acc,none,0.4362745098039216,0.03480693138457044,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/102b4d2167_2026-09-30T07-34-14.607890.json,1790753469.301372,1 +v2anneal_120k,sib200_ron_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/78576cf6ae_2026-09-30T07-40-32.592661.json,1790753865.3778918,1 +v2anneal_120k,sib200_slk_Latn,0,lm-eval,vllm,,acc,none,0.36764705882352944,0.0338413204567412,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7fc4481f5b_2026-09-30T08-38-48.224315.json,1790757372.8077683,1 +v2anneal_120k,sib200_slv_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b6508c69a1_2026-09-30T07-44-37.127181.json,1790754112.398617,1 +v2anneal_120k,sib200_spa_Latn,0,lm-eval,vllm,,acc,none,0.4117647058823529,0.03454236585380609,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/3856e98830_2026-09-30T08-16-50.403991.json,1790756044.1519241,1 +v2anneal_120k,sib200_srp_Cyrl,0,lm-eval,vllm,,acc,none,0.4019607843137255,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/dfe8fe4ce8_2026-09-30T07-34-14.844439.json,1790753469.4979644,1 +v2anneal_120k,sib200_swe_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b036b8da24_2026-09-30T07-40-22.728172.json,1790753866.3781729,1 +v2anneal_120k,sib200_tur_Latn,0,lm-eval,vllm,,acc,none,0.4264705882352941,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/c7f2104b97_2026-09-30T07-42-27.448626.json,1790753985.941826,1 +v2anneal_120k,sib200_ukr_Cyrl,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/e85261cdea_2026-09-30T08-39-04.286010.json,1790757380.7491508,1 +v2anneal_120k,social_iqa,0,lm-eval,vllm,,acc,none,0.529682702149437,0.011294116144908325,1954,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/b410dc9345_2026-09-30T07-34-31.794303.json,1790753468.547855,1 +v2anneal_120k,squadv2,10,lm-eval,vllm,,HasAns_exact,none,80.3306342780027,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 +v2anneal_120k,squadv2,10,lm-eval,vllm,,HasAns_f1,none,86.54862172736328,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 +v2anneal_120k,squadv2,10,lm-eval,vllm,,NoAns_exact,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 +v2anneal_120k,squadv2,10,lm-eval,vllm,,NoAns_f1,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 +v2anneal_120k,squadv2,10,lm-eval,vllm,,best_exact,none,58.44352733091889,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 +v2anneal_120k,squadv2,10,lm-eval,vllm,,best_f1,none,59.64883767726625,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 +v2anneal_120k,squadv2,10,lm-eval,vllm,,exact,none,40.10780763075886,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 +v2anneal_120k,squadv2,10,lm-eval,vllm,,f1,none,43.212349835745776,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/014b89082e_2026-09-30T09-22-06.311527.json,1790758108.8443446,1 +v2anneal_120k,winogrande,0,lm-eval,vllm,,acc,none,0.7190213101815311,0.012632541095875895,1267,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/5e2c321f9a_2026-09-30T08-21-12.061404.json,1790756304.2532954,1 +v2anneal_120k,wsc273,0,lm-eval,vllm,,acc,none,0.8534798534798534,0.021441781058034026,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/53cda4f058_2026-09-30T08-29-16.068117.json,1790756790.8583784,1 +v2anneal_120k,xcopa:et,0,lighteval,hf/accelerate,,acc,none,0.65,0.021352091786223104,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/e232988303/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-33-03.727328.json,1790753583.8088856,1 +v2anneal_120k,xcopa:it,0,lighteval,hf/accelerate,,acc,none,0.684,0.02081235951585585,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/82ecdec95b/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-41-01.290183.json,1790754061.374489,1 +v2anneal_120k,xcopa:tr,0,lighteval,hf/accelerate,,acc,none,0.648,0.02138004238594606,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/lighteval/2026-09-30-09-21-35/results/1cc83494eb/results/e/scratch/e-sta-openeurollm/vanosch1/flag-evals-test3/views/plain/v2anneal_120k/results_2026-09-30T07-33-03.728498.json,1790753583.81116,1 +v2anneal_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc,none,0.47,0.015790799515836725,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d2d5c2cc22_2026-09-30T08-32-38.152605.json,1790756982.5484955,1 +v2anneal_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc_norm,none,0.445,0.015723301886761007,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/d2d5c2cc22_2026-09-30T08-32-38.152605.json,1790756982.5484955,1 +v2anneal_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc,none,0.644,0.015149042659306678,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/59ec13a078_2026-09-30T08-45-22.591132.json,1790757750.4307208,1 +v2anneal_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc_norm,none,0.618,0.015372453034968502,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/59ec13a078_2026-09-30T08-45-22.591132.json,1790757750.4307208,1 +v2anneal_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc,none,0.466,0.015782683329937694,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/03704b7c15_2026-09-30T08-10-59.172998.json,1790754223.6783261,1 +v2anneal_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc_norm,none,0.433,0.01567663091218125,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/03704b7c15_2026-09-30T08-10-59.172998.json,1790754223.6783261,1 +v2anneal_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc,none,0.487,0.015813952101896636,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f29465a9a6_2026-09-30T07-34-36.924944.json,1790753512.0613227,1 +v2anneal_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc_norm,none,0.434,0.015680876566375044,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/f29465a9a6_2026-09-30T07-34-36.924944.json,1790753512.0613227,1 +v2anneal_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc,none,0.461,0.015771104201283047,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c9fb60d65_2026-09-30T08-47-38.218202.json,1790757888.217367,1 +v2anneal_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc_norm,none,0.432,0.015672320237336324,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/8c9fb60d65_2026-09-30T08-47-38.218202.json,1790757888.217367,1 +v2anneal_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc,none,0.396,0.015473313265859495,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7444a7ac74_2026-09-30T08-45-26.694718.json,1790757756.5939891,1 +v2anneal_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc_norm,none,0.378,0.015341165254026547,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/7444a7ac74_2026-09-30T08-45-26.694718.json,1790757756.5939891,1 +v2anneal_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.459,0.015766025737882314,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/761634c7af_2026-09-30T08-52-24.622753.json,1790758111.541365,1 +v2anneal_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.44,0.015704987954361718,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/761634c7af_2026-09-30T08-52-24.622753.json,1790758111.541365,1 +v2anneal_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.461,0.015771104201283047,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/48a1da8d08_2026-09-30T07-40-37.787207.json,1790753866.2360377,1 +v2anneal_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.41,0.015560917136921659,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/vllm/2026-09-30-09-21-34/results/48a1da8d08_2026-09-30T07-40-37.787207.json,1790753866.2360377,1 +v2anneal_120k,aime24_cot,0,lm-eval,vllm,,pass@1,all,0.20833333333333334,0.056088796253209956,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/1b80421fff_2026-10-08T17-36-23.530370.json,1791479849.4084291,1 +v2anneal_120k,aime24_cot,0,lm-eval,vllm,,pass@16,all,0.45459370673086397,0.09059048210652604,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/1b80421fff_2026-10-08T17-36-23.530370.json,1791479849.4084291,1 +v2anneal_120k,aime24_cot,0,lm-eval,vllm,,pass@32,all,0.4666666666666667,0.09264111117062016,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/1b80421fff_2026-10-08T17-36-23.530370.json,1791479849.4084291,1 +v2anneal_120k,aime24_cot,0,lm-eval,vllm,,pass@4,all,0.3536827956989247,0.07723800493932856,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/1b80421fff_2026-10-08T17-36-23.530370.json,1791479849.4084291,1 +v2anneal_120k,aime24_cot,0,lm-eval,vllm,,think_closed,all,0.21041666666666667,0.05665826721048764,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/1b80421fff_2026-10-08T17-36-23.530370.json,1791479849.4084291,1 +v2anneal_120k,aime25_cot,0,lm-eval,vllm,,pass@1,all,0.19791666666666666,0.06302461812991378,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/668d944b2a_2026-10-08T17-36-28.652790.json,1791479852.5430236,1 +v2anneal_120k,aime25_cot,0,lm-eval,vllm,,pass@16,all,0.37353984292627923,0.08330477196529634,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/668d944b2a_2026-10-08T17-36-28.652790.json,1791479852.5430236,1 +v2anneal_120k,aime25_cot,0,lm-eval,vllm,,pass@32,all,0.43333333333333335,0.09201865544655373,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/668d944b2a_2026-10-08T17-36-28.652790.json,1791479852.5430236,1 +v2anneal_120k,aime25_cot,0,lm-eval,vllm,,pass@4,all,0.2843604004449388,0.07546972788269583,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/668d944b2a_2026-10-08T17-36-28.652790.json,1791479852.5430236,1 +v2anneal_120k,aime25_cot,0,lm-eval,vllm,,think_closed,all,0.21979166666666666,0.06591740639615737,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/668d944b2a_2026-10-08T17-36-28.652790.json,1791479852.5430236,1 +v2anneal_120k,amc23_cot,0,lm-eval,vllm,,pass@1,all,0.54609375,0.06108153486318092,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/aa3b82d7e6_2026-10-08T17-36-51.775200.json,1791479855.2446117,1 +v2anneal_120k,amc23_cot,0,lm-eval,vllm,,pass@16,all,0.9048267390656347,0.04218558676303891,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/aa3b82d7e6_2026-10-08T17-36-51.775200.json,1791479855.2446117,1 +v2anneal_120k,amc23_cot,0,lm-eval,vllm,,pass@32,all,0.925,0.04217636961434867,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/aa3b82d7e6_2026-10-08T17-36-51.775200.json,1791479855.2446117,1 +v2anneal_120k,amc23_cot,0,lm-eval,vllm,,pass@4,all,0.7514919354838709,0.05162845807508801,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/aa3b82d7e6_2026-10-08T17-36-51.775200.json,1791479855.2446117,1 +v2anneal_120k,amc23_cot,0,lm-eval,vllm,,think_closed,all,0.528125,0.06323486250905004,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/aa3b82d7e6_2026-10-08T17-36-51.775200.json,1791479855.2446117,1 +v2anneal_120k,gpqa_diamond_cot,0,lm-eval,vllm,,pass@1,all,0.44823232323232326,0.028712516194078747,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/fac130d06e_2026-10-08T17-44-11.115236.json,1791479856.780032,1 +v2anneal_120k,gpqa_diamond_cot,0,lm-eval,vllm,,think_closed,all,0.32702020202020204,0.027911613045990397,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/fac130d06e_2026-10-08T17-44-11.115236.json,1791479856.780032,1 +v2anneal_120k,humaneval_cont,0,lm-eval,vllm,,pass@1,all,0.6659679878048781,0.030530454904218768,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/98160f13ec_2026-10-08T17-34-08.413785.json,1791480551.5540006,1 +v2anneal_120k,humaneval_cont,0,lm-eval,vllm,,pass@16,all,0.8465700371382368,0.02697432000810755,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/98160f13ec_2026-10-08T17-34-08.413785.json,1791480551.5540006,1 +v2anneal_120k,jeebench_cot,0,lm-eval,vllm,,pass@1,all,0.33046116504854367,0.01701352016032047,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/4479146c6b_2026-10-08T17-50-58.715735.json,1791479849.4084687,1 +v2anneal_120k,jeebench_cot,0,lm-eval,vllm,,pass@4,all,0.487378640776699,0.022047027085087385,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/4479146c6b_2026-10-08T17-50-58.715735.json,1791479849.4084687,1 +v2anneal_120k,jeebench_cot,0,lm-eval,vllm,,think_closed,all,0.38300970873786405,0.017331500976929773,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/4479146c6b_2026-10-08T17-50-58.715735.json,1791479849.4084687,1 +v2anneal_120k,livecodebench_cont,0,lm-eval,vllm,,pass@1,all,0.16462818003913895,0.014287300964789537,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/2d98b7c58b_2026-10-08T21-27-21.057817.json,1791492002.2412536,1 +v2anneal_120k,livecodebench_cont,0,lm-eval,vllm,,pass@4,all,0.24050880626223092,0.017899565713087876,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/2d98b7c58b_2026-10-08T21-27-21.057817.json,1791492002.2412536,1 +v2anneal_120k,math500_cot,0,lm-eval,vllm,,pass@1,all,0.7335,0.01737265432328845,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/e11dd441ec_2026-10-08T17-38-57.269963.json,1791479855.034017,1 +v2anneal_120k,math500_cot,0,lm-eval,vllm,,pass@4,all,0.836,0.016575811142446696,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/e11dd441ec_2026-10-08T17-38-57.269963.json,1791479855.034017,1 +v2anneal_120k,math500_cot,0,lm-eval,vllm,,think_closed,all,0.779,0.01625874206040472,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/e11dd441ec_2026-10-08T17-38-57.269963.json,1791479855.034017,1 +v2anneal_120k,mbpp_cont,3,lm-eval,vllm,,pass@1,all,0.6215,0.01921819914447536,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/9558744df6_2026-10-08T17-45-31.996681.json,1791481114.884159,1 +v2anneal_120k,mbpp_cont,3,lm-eval,vllm,,pass@16,all,0.7643449609959826,0.018675960756148607,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/9558744df6_2026-10-08T17-45-31.996681.json,1791481114.884159,1 +v2anneal_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@1,all,0.066,0.020896056118088945,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/ed3d40240c_2026-10-08T17-29-40.205217.json,1791479849.6305587,1 +v2anneal_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@4,all,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/ed3d40240c_2026-10-08T17-29-40.205217.json,1791479849.6305587,1 +v2anneal_120k,polymath_de_high_cot,0,lm-eval,vllm,,think_closed,all,0.074,0.021631816471830743,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/ed3d40240c_2026-10-08T17-29-40.205217.json,1791479849.6305587,1 +v2anneal_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@1,all,0.756,0.03460188322303635,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/233163cb5b_2026-10-08T17-23-25.967368.json,1791479853.783528,1 +v2anneal_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@4,all,0.848,0.032241027759172654,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/233163cb5b_2026-10-08T17-23-25.967368.json,1791479853.783528,1 +v2anneal_120k,polymath_de_low_cot,0,lm-eval,vllm,,think_closed,all,0.938,0.019604147026717617,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/233163cb5b_2026-10-08T17-23-25.967368.json,1791479853.783528,1 +v2anneal_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@1,all,0.218,0.03347796579167239,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/babeb862e5_2026-10-08T17-29-27.700926.json,1791479851.0448537,1 +v2anneal_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@4,all,0.28,0.04032129030193482,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/babeb862e5_2026-10-08T17-29-27.700926.json,1791479851.0448537,1 +v2anneal_120k,polymath_de_medium_cot,0,lm-eval,vllm,,think_closed,all,0.26,0.03482676019681491,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/babeb862e5_2026-10-08T17-29-27.700926.json,1791479851.0448537,1 +v2anneal_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.00563399817925698,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/528b8829fd_2026-10-08T17-29-35.508616.json,1791479849.9268932,1 +v2anneal_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/528b8829fd_2026-10-08T17-29-35.508616.json,1791479849.9268932,1 +v2anneal_120k,polymath_de_top_cot,0,lm-eval,vllm,,think_closed,all,0.016,0.007902633289178096,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/528b8829fd_2026-10-08T17-29-35.508616.json,1791479849.9268932,1 +v2anneal_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@1,all,0.08,0.021552636243212988,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/3b97bcc2e9_2026-10-08T17-29-37.875917.json,1791479849.5044763,1 +v2anneal_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@4,all,0.112,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/3b97bcc2e9_2026-10-08T17-29-37.875917.json,1791479849.5044763,1 +v2anneal_120k,polymath_en_high_cot,0,lm-eval,vllm,,think_closed,all,0.092,0.022276850417330747,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/3b97bcc2e9_2026-10-08T17-29-37.875917.json,1791479849.5044763,1 +v2anneal_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@1,all,0.88,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/7f9c48fbf6_2026-10-08T17-25-39.825933.json,1791479991.3512816,1 +v2anneal_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@4,all,0.944,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/7f9c48fbf6_2026-10-08T17-25-39.825933.json,1791479991.3512816,1 +v2anneal_120k,polymath_en_low_cot,0,lm-eval,vllm,,think_closed,all,0.972,0.01178298390380889,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/7f9c48fbf6_2026-10-08T17-25-39.825933.json,1791479991.3512816,1 +v2anneal_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@1,all,0.208,0.03644881519380648,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/06315b8049_2026-10-08T17-29-38.645365.json,1791479851.7353542,1 +v2anneal_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@4,all,0.208,0.03644881519380648,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/06315b8049_2026-10-08T17-29-38.645365.json,1791479851.7353542,1 +v2anneal_120k,polymath_en_medium_cot,0,lm-eval,vllm,,think_closed,all,0.288,0.04066543273291013,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/06315b8049_2026-10-08T17-29-38.645365.json,1791479851.7353542,1 +v2anneal_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/6438b60ba7_2026-10-08T17-31-59.036952.json,1791479987.5275068,1 +v2anneal_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/6438b60ba7_2026-10-08T17-31-59.036952.json,1791479987.5275068,1 +v2anneal_120k,polymath_en_top_cot,0,lm-eval,vllm,,think_closed,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/6438b60ba7_2026-10-08T17-31-59.036952.json,1791479987.5275068,1 +v2anneal_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@1,all,0.08,0.02192362108070477,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/54573a5543_2026-10-08T17-29-50.110522.json,1791479849.6126356,1 +v2anneal_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@4,all,0.112,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/54573a5543_2026-10-08T17-29-50.110522.json,1791479849.6126356,1 +v2anneal_120k,polymath_es_high_cot,0,lm-eval,vllm,,think_closed,all,0.094,0.023702456657758136,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/54573a5543_2026-10-08T17-29-50.110522.json,1791479849.6126356,1 +v2anneal_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@1,all,0.794,0.027542342768204928,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/6489843d83_2026-10-08T17-23-27.812570.json,1791479850.7272031,1 +v2anneal_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@4,all,0.936,0.021979462554702022,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/6489843d83_2026-10-08T17-23-27.812570.json,1791479850.7272031,1 +v2anneal_120k,polymath_es_low_cot,0,lm-eval,vllm,,think_closed,all,0.954,0.014307678966881903,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/6489843d83_2026-10-08T17-23-27.812570.json,1791479850.7272031,1 +v2anneal_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@1,all,0.208,0.031716485994999,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/1857ebd3d3_2026-10-08T17-29-33.705309.json,1791479855.016976,1 +v2anneal_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@4,all,0.288,0.04066543273291013,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/1857ebd3d3_2026-10-08T17-29-33.705309.json,1791479855.016976,1 +v2anneal_120k,polymath_es_medium_cot,0,lm-eval,vllm,,think_closed,all,0.252,0.03389928156056675,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/1857ebd3d3_2026-10-08T17-29-33.705309.json,1791479855.016976,1 +v2anneal_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/7c0ff1fd21_2026-10-08T17-29-43.139196.json,1791479856.7044358,1 +v2anneal_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/7c0ff1fd21_2026-10-08T17-29-43.139196.json,1791479856.7044358,1 +v2anneal_120k,polymath_es_top_cot,0,lm-eval,vllm,,think_closed,all,0.016,0.007902633289178096,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/7c0ff1fd21_2026-10-08T17-29-43.139196.json,1791479856.7044358,1 +v2anneal_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@1,all,0.072,0.02159300962154486,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/b1b7ed95b5_2026-10-08T17-29-33.867849.json,1791479854.6151934,1 +v2anneal_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@4,all,0.104,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/b1b7ed95b5_2026-10-08T17-29-33.867849.json,1791479854.6151934,1 +v2anneal_120k,polymath_fr_high_cot,0,lm-eval,vllm,,think_closed,all,0.108,0.026079283584064663,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/b1b7ed95b5_2026-10-08T17-29-33.867849.json,1791479854.6151934,1 +v2anneal_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@1,all,0.824,0.028116118669408444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/76f3a55fc3_2026-10-08T17-23-39.139614.json,1791479852.0811234,1 +v2anneal_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@4,all,0.912,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/76f3a55fc3_2026-10-08T17-23-39.139614.json,1791479852.0811234,1 +v2anneal_120k,polymath_fr_low_cot,0,lm-eval,vllm,,think_closed,all,0.954,0.015653506254654774,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/76f3a55fc3_2026-10-08T17-23-39.139614.json,1791479852.0811234,1 +v2anneal_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@1,all,0.218,0.03383737197146793,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/0d0a184645_2026-10-08T17-31-58.189159.json,1791479990.4415627,1 +v2anneal_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@4,all,0.304,0.041307657651398745,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/0d0a184645_2026-10-08T17-31-58.189159.json,1791479990.4415627,1 +v2anneal_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,think_closed,all,0.278,0.03661217847797677,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/0d0a184645_2026-10-08T17-31-58.189159.json,1791479990.4415627,1 +v2anneal_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@1,all,0.01,0.005956833971812705,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/f40edef5e0_2026-10-08T17-29-35.362160.json,1791479849.4084868,1 +v2anneal_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@4,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/f40edef5e0_2026-10-08T17-29-35.362160.json,1791479849.4084868,1 +v2anneal_120k,polymath_fr_top_cot,0,lm-eval,vllm,,think_closed,all,0.02,0.008798826901281196,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/f40edef5e0_2026-10-08T17-29-35.362160.json,1791479849.4084868,1 +v2anneal_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@1,all,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/8b9c81be46_2026-10-08T17-31-59.559308.json,1791479990.4145443,1 +v2anneal_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@4,all,0.072,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/8b9c81be46_2026-10-08T17-31-59.559308.json,1791479990.4145443,1 +v2anneal_120k,polymath_it_high_cot,0,lm-eval,vllm,,think_closed,all,0.08,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/8b9c81be46_2026-10-08T17-31-59.559308.json,1791479990.4145443,1 +v2anneal_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@1,all,0.836,0.027694182456528372,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/2b02560e42_2026-10-08T17-23-28.270610.json,1791479851.325732,1 +v2anneal_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@4,all,0.944,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/2b02560e42_2026-10-08T17-23-28.270610.json,1791479851.325732,1 +v2anneal_120k,polymath_it_low_cot,0,lm-eval,vllm,,think_closed,all,0.944,0.018808028484768705,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/2b02560e42_2026-10-08T17-23-28.270610.json,1791479851.325732,1 +v2anneal_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@1,all,0.226,0.03436333379748565,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/274737826f_2026-10-08T17-29-24.145296.json,1791479849.8860953,1 +v2anneal_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@4,all,0.296,0.04099409870984186,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/274737826f_2026-10-08T17-29-24.145296.json,1791479849.8860953,1 +v2anneal_120k,polymath_it_medium_cot,0,lm-eval,vllm,,think_closed,all,0.268,0.0362758250612025,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/274737826f_2026-10-08T17-29-24.145296.json,1791479849.8860953,1 +v2anneal_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@1,all,0.006,0.004457686366483794,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/32341dbbf8_2026-10-08T17-29-45.650895.json,1791479858.8864896,1 +v2anneal_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@4,all,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/32341dbbf8_2026-10-08T17-29-45.650895.json,1791479858.8864896,1 +v2anneal_120k,polymath_it_top_cot,0,lm-eval,vllm,,think_closed,all,0.026,0.010558592281537438,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/32341dbbf8_2026-10-08T17-29-45.650895.json,1791479858.8864896,1 +v2anneal_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@1,all,0.088,0.02294031526627585,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/951b51033a_2026-10-08T17-29-31.830644.json,1791479850.0477571,1 +v2anneal_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@4,all,0.12,0.029182407426835203,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/951b51033a_2026-10-08T17-29-31.830644.json,1791479850.0477571,1 +v2anneal_120k,polymath_pt_high_cot,0,lm-eval,vllm,,think_closed,all,0.102,0.025095944923690428,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/951b51033a_2026-10-08T17-29-31.830644.json,1791479850.0477571,1 +v2anneal_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@1,all,0.792,0.03222101097711083,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/424cda1913_2026-10-08T17-25-57.746500.json,1791479992.3405397,1 +v2anneal_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@4,all,0.896,0.027413206141707357,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/424cda1913_2026-10-08T17-25-57.746500.json,1791479992.3405397,1 +v2anneal_120k,polymath_pt_low_cot,0,lm-eval,vllm,,think_closed,all,0.944,0.018808028484768705,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/424cda1913_2026-10-08T17-25-57.746500.json,1791479992.3405397,1 +v2anneal_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@1,all,0.236,0.03516137910613236,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/984e2b01df_2026-10-08T17-31-34.507119.json,1791479991.514768,1 +v2anneal_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@4,all,0.312,0.041606451112700636,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/984e2b01df_2026-10-08T17-31-34.507119.json,1791479991.514768,1 +v2anneal_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,think_closed,all,0.29,0.03782387025795116,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/984e2b01df_2026-10-08T17-31-34.507119.json,1791479991.514768,1 +v2anneal_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/35355d00f8_2026-10-08T17-32-01.193942.json,1791479997.95539,1 +v2anneal_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/35355d00f8_2026-10-08T17-32-01.193942.json,1791479997.95539,1 +v2anneal_120k,polymath_pt_top_cot,0,lm-eval,vllm,,think_closed,all,0.006,0.003436051747704511,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_120k/cot/2026-10-08-19-13-37/results/35355d00f8_2026-10-08T17-32-01.193942.json,1791479997.95539,1 diff --git a/results/v2anneal_merge3_116k_120k.flag-evals-471.tasks.csv b/results/v2anneal_merge3_116k_120k.flag-evals-471.tasks.csv new file mode 100644 index 0000000..ee3dd37 --- /dev/null +++ b/results/v2anneal_merge3_116k_120k.flag-evals-471.tasks.csv @@ -0,0 +1,2124 @@ +checkpoint,task,n_shot,harness,backend,is_group,metric,filter,value,stderr,n_samples,results_file,result_time,n_files +v2anneal_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,accuracy_avg,,0.16666666666666669,0.0047140452079103175,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/dc7991a63c/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T17-25-00.570949.json,1791393896.2356632,1 +v2anneal_merge3_116k_120k,AIME24,0,Evalchemy,vllm,,solved_avg,,5.0,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/dc7991a63c/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T17-25-00.570949.json,1791393896.2356632,1 +v2anneal_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,accuracy_avg,,0.2266666666666667,0.004216370213557839,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d37ec8bc36/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T17-05-25.164228.json,1791392721.2198527,1 +v2anneal_merge3_116k_120k,AIME25,0,Evalchemy,vllm,,solved_avg,,6.8,,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d37ec8bc36/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T17-05-25.164228.json,1791392721.2198527,1 +v2anneal_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,accuracy_avg,,0.3825,0.0127720397744448,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/53a09bd9b5/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-35-44.786133.json,1791390937.001752,1 +v2anneal_merge3_116k_120k,AMC23,0,Evalchemy,vllm,,solved_avg,,15.3,,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/53a09bd9b5/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-35-44.786133.json,1791390937.001752,1 +v2anneal_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,accuracy_avg,,0.3367003367003367,0.013112594214980842,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4b3a3df7e1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-50-48.079279.json,1791391843.712647,1 +v2anneal_merge3_116k_120k,GPQADiamond,0,Evalchemy,vllm,,solved_avg,,66.66666666666667,,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4b3a3df7e1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-50-48.079279.json,1791391843.712647,1 +v2anneal_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,python_pass@1,,0.22560975609756098,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/03bc0cb946/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-12-13.661419.json,1791389530.0225797,1 +v2anneal_merge3_116k_120k,HumanEval,0,Evalchemy,vllm,,sh_pass@1,,0.006329113924050633,,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/03bc0cb946/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-12-13.661419.json,1791389530.0225797,1 +v2anneal_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,accuracy_avg,,0.26666666666666666,0.002520673451035147,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d49ec2b051/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-35-44.990390.json,1791390940.208877,1 +v2anneal_merge3_116k_120k,JEEBench,0,Evalchemy,vllm,,solved_avg,,137.33333333333334,,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d49ec2b051/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-35-44.990390.json,1791390940.208877,1 +v2anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_avg,,0.17090671885192432,0.0021237861182126162,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f6176791a1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-55-37.853219.json,1791392134.2753317,1 +v2anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_easy_avg,,0.38095238095238093,0.003928133807605714,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f6176791a1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-55-37.853219.json,1791392134.2753317,1 +v2anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_hard_avg,,0.0,0.0,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f6176791a1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-55-37.853219.json,1791392134.2753317,1 +v2anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,accuracy_medium_avg,,0.08737864077669903,0.0039635756355714865,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f6176791a1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-55-37.853219.json,1791392134.2753317,1 +v2anneal_merge3_116k_120k,LiveCodeBench,0,Evalchemy,vllm,,solved_avg,,87.33333333333333,,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f6176791a1/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-55-37.853219.json,1791392134.2753317,1 +v2anneal_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,accuracy,,0.448,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/076537b593/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-39-40.300622.json,1791391175.540568,1 +v2anneal_merge3_116k_120k,MATH500,0,Evalchemy,vllm,,num_solved,,224,,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/076537b593/__e__scratch__e-sta-openeurollm__poeppel1__flag-evals__views__identity__v2anneal_merge3_116k_120k/results_2026-10-07T16-39-40.300622.json,1791391175.540568,1 +v2anneal_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc,none,0.26956521739130435,0.029322764228949562,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/88ed6f507d_2026-10-07T16-07-25.798873.json,1791389073.9476888,1 +v2anneal_merge3_116k_120k,agieval_lsat_ar,3,lm-eval,vllm,,acc_norm,none,0.26521739130434785,0.029171764078472565,230,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/88ed6f507d_2026-10-07T16-07-25.798873.json,1791389073.9476888,1 +v2anneal_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc,none,0.6228668941979523,0.01416336689619262,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/54f33379f9_2026-10-07T16-30-06.772378.json,1791390422.6279137,1 +v2anneal_merge3_116k_120k,arc_challenge,10,lm-eval,vllm,,acc_norm,none,0.6544368600682594,0.013896938461145866,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/54f33379f9_2026-10-07T16-30-06.772378.json,1791390422.6279137,1 +v2anneal_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc,none,0.6373720136518771,0.014049106564955149,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d5b03ce677_2026-10-07T16-08-08.484185.json,1791389066.5693853,1 +v2anneal_merge3_116k_120k,arc_challenge,25,lm-eval,vllm,,acc_norm,none,0.6706484641638225,0.013734057652635537,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d5b03ce677_2026-10-07T16-08-08.484185.json,1791389066.5693853,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc,none,0.5418088737201365,0.014560220308714553,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1d074facd_2026-10-07T16-34-50.485534.json,1791390655.8705962,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_bg,25,lm-eval,vllm,,acc_norm,none,0.5895904436860068,0.014374922192642638,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1d074facd_2026-10-07T16-34-50.485534.json,1791390655.8705962,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc,none,0.5392491467576792,0.014566303676636534,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3e77f39685_2026-10-07T16-08-21.483120.json,1791389074.3095648,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_cs,25,lm-eval,vllm,,acc_norm,none,0.5631399317406144,0.014494421584256512,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3e77f39685_2026-10-07T16-08-21.483120.json,1791389074.3095648,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc,none,0.5443686006825939,0.014553749939306847,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/528b9aa4c9_2026-10-07T16-24-44.900963.json,1791390053.9545755,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_da,25,lm-eval,vllm,,acc_norm,none,0.5767918088737202,0.014438036220848015,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/528b9aa4c9_2026-10-07T16-24-44.900963.json,1791390053.9545755,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc,none,0.5196245733788396,0.014600132075947018,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2850d74d7f_2026-10-07T16-10-39.016508.json,1791389206.4182372,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_de,25,lm-eval,vllm,,acc_norm,none,0.5520477815699659,0.014532011498211617,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2850d74d7f_2026-10-07T16-10-39.016508.json,1791389206.4182372,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc,none,0.5170648464163823,0.014602878388536583,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/99f40b56fe_2026-10-07T16-12-52.686997.json,1791389320.6700156,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_el,25,lm-eval,vllm,,acc_norm,none,0.5580204778156996,0.014512682523128238,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/99f40b56fe_2026-10-07T16-12-52.686997.json,1791389320.6700156,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc,none,0.5776450511945392,0.014434138713379965,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4edd7603b6_2026-10-07T16-45-07.019304.json,1791391272.7241483,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_es,25,lm-eval,vllm,,acc_norm,none,0.6194539249146758,0.014188277712349937,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4edd7603b6_2026-10-07T16-45-07.019304.json,1791391272.7241483,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc,none,0.5127986348122867,0.014606603181012609,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/03169e8ca6_2026-10-07T16-08-31.782978.json,1791389075.927568,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_et,25,lm-eval,vllm,,acc_norm,none,0.5281569965870307,0.014588204105102335,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/03169e8ca6_2026-10-07T16-08-31.782978.json,1791389075.927568,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc,none,0.48293515358361777,0.014602878388536585,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/58cef210c7_2026-10-07T16-40-56.403847.json,1791391023.7084582,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_fi,25,lm-eval,vllm,,acc_norm,none,0.5332764505119454,0.0145789958596058,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/58cef210c7_2026-10-07T16-40-56.403847.json,1791391023.7084582,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e2fd8c1d19_2026-10-07T16-34-59.785625.json,1791390659.7214282,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_fr,25,lm-eval,vllm,,acc_norm,none,0.6109215017064846,0.014247309976045494,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e2fd8c1d19_2026-10-07T16-34-59.785625.json,1791390659.7214282,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc,none,0.5102389078498294,0.014608326906285005,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/55b290bf69_2026-10-07T16-32-56.430441.json,1791390540.1956072,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_hu,25,lm-eval,vllm,,acc_norm,none,0.5409556313993175,0.01456229107360112,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/55b290bf69_2026-10-07T16-32-56.430441.json,1791390540.1956072,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc,none,0.5,0.014611390804670088,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/107f831a4e_2026-10-07T16-10-31.694889.json,1791389193.7672904,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_is,25,lm-eval,vllm,,acc_norm,none,0.5315699658703071,0.014582236460866984,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/107f831a4e_2026-10-07T16-10-31.694889.json,1791389193.7672904,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc,none,0.5665529010238908,0.014481376224558896,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/74591adf98_2026-10-07T16-12-34.733759.json,1791389324.4349437,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_it,25,lm-eval,vllm,,acc_norm,none,0.6040955631399317,0.01429122839353657,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/74591adf98_2026-10-07T16-12-34.733759.json,1791389324.4349437,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc,none,0.5298634812286689,0.014585305840007116,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ebc697588c_2026-10-07T16-38-57.048455.json,1791390904.3597214,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_lt,25,lm-eval,vllm,,acc_norm,none,0.5477815699658704,0.014544519880633823,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ebc697588c_2026-10-07T16-38-57.048455.json,1791390904.3597214,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc,none,0.5204778156996587,0.01459913135303498,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/283ea1a2dc_2026-10-07T16-15-01.318393.json,1791389444.672676,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_lv,25,lm-eval,vllm,,acc_norm,none,0.5366894197952219,0.014572000527756918,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/283ea1a2dc_2026-10-07T16-15-01.318393.json,1791389444.672676,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc,none,0.5341296928327645,0.014577311315231023,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/01ab2c4d52_2026-10-07T16-08-40.862396.json,1791389087.6926284,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_nb,25,lm-eval,vllm,,acc_norm,none,0.5767918088737202,0.014438036220848015,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/01ab2c4d52_2026-10-07T16-08-40.862396.json,1791389087.6926284,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc,none,0.5358361774744027,0.014573813664735622,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/dc36651d52_2026-10-07T16-28-53.444783.json,1791390295.843359,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_nl,25,lm-eval,vllm,,acc_norm,none,0.5597269624573379,0.014506769524804264,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/dc36651d52_2026-10-07T16-28-53.444783.json,1791390295.843359,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc,none,0.5307167235494881,0.014583792546304033,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/11aa048887_2026-10-07T16-14-27.440222.json,1791389437.4574344,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_pl,25,lm-eval,vllm,,acc_norm,none,0.5520477815699659,0.014532011498211617,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/11aa048887_2026-10-07T16-14-27.440222.json,1791389437.4574344,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc,none,0.5674061433447098,0.014478005694182441,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2e74ae0182_2026-10-07T16-12-26.363465.json,1791389316.1188269,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_pt,25,lm-eval,vllm,,acc_norm,none,0.6168941979522184,0.01420647266167275,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2e74ae0182_2026-10-07T16-12-26.363465.json,1791389316.1188269,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc,none,0.5537542662116041,0.014526705548539945,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/75c0d1af27_2026-10-07T16-45-37.928841.json,1791391286.932935,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_ro,25,lm-eval,vllm,,acc_norm,none,0.5853242320819113,0.014397070564409184,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/75c0d1af27_2026-10-07T16-45-37.928841.json,1791391286.932935,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc,none,0.5477815699658704,0.014544519880633823,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/bb9899ba06_2026-10-07T16-34-51.225457.json,1791390662.730336,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_sk,25,lm-eval,vllm,,acc_norm,none,0.575938566552901,0.014441889627464344,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/bb9899ba06_2026-10-07T16-34-51.225457.json,1791390662.730336,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc,none,0.5349829351535836,0.014575583922019714,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/43afeec4b6_2026-10-07T16-45-06.819766.json,1791391275.7946942,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_sl,25,lm-eval,vllm,,acc_norm,none,0.5631399317406144,0.014494421584256512,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/43afeec4b6_2026-10-07T16-45-06.819766.json,1791391275.7946942,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc,none,0.537542662116041,0.014570144495075503,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1553ad3e5b_2026-10-07T16-45-08.593951.json,1791391278.6138303,1 +v2anneal_merge3_116k_120k,arc_challenge_mt_sv,25,lm-eval,vllm,,acc_norm,none,0.5810580204778157,0.01441810695363902,1172,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1553ad3e5b_2026-10-07T16-45-08.593951.json,1791391278.6138303,1 +v2anneal_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc,none,0.8665824915824916,0.006977174118514789,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8538de6f22_2026-10-07T16-44-46.227684.json,1791391271.8764184,1 +v2anneal_merge3_116k_120k,arc_easy,10,lm-eval,vllm,,acc_norm,none,0.8775252525252525,0.006726997725762857,2376,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8538de6f22_2026-10-07T16-44-46.227684.json,1791391271.8764184,1 +v2anneal_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1140e68c50_2026-10-07T16-19-48.038242.json,1791389808.4425204,1 +v2anneal_merge3_116k_120k,belebele_bul_Cyrl,5,lm-eval,vllm,,acc_norm,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1140e68c50_2026-10-07T16-19-48.038242.json,1791389808.4425204,1 +v2anneal_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/56b546ed44_2026-10-07T16-35-59.868741.json,1791390787.9580464,1 +v2anneal_merge3_116k_120k,belebele_ces_Latn,5,lm-eval,vllm,,acc_norm,none,0.9033333333333333,0.009855588084302997,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/56b546ed44_2026-10-07T16-35-59.868741.json,1791390787.9580464,1 +v2anneal_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc,none,0.8988888888888888,0.010054780672527,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/804968a851_2026-10-07T16-38-02.997747.json,1791390900.2753065,1 +v2anneal_merge3_116k_120k,belebele_dan_Latn,5,lm-eval,vllm,,acc_norm,none,0.8988888888888888,0.010054780672527,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/804968a851_2026-10-07T16-38-02.997747.json,1791390900.2753065,1 +v2anneal_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/db2c26c368_2026-10-07T16-23-51.134562.json,1791390049.4055755,1 +v2anneal_merge3_116k_120k,belebele_deu_Latn,5,lm-eval,vllm,,acc_norm,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/db2c26c368_2026-10-07T16-23-51.134562.json,1791390049.4055755,1 +v2anneal_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f6cf38d41e_2026-10-07T16-23-45.748096.json,1791390048.2330267,1 +v2anneal_merge3_116k_120k,belebele_ell_Grek,5,lm-eval,vllm,,acc_norm,none,0.9066666666666666,0.009702024502458153,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f6cf38d41e_2026-10-07T16-23-45.748096.json,1791390048.2330267,1 +v2anneal_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc,none,0.9277777777777778,0.008633314476063626,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4dbd560dd9_2026-10-07T16-40-08.005918.json,1791391033.7656484,1 +v2anneal_merge3_116k_120k,belebele_eng_Latn,5,lm-eval,vllm,,acc_norm,none,0.9277777777777778,0.008633314476063626,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4dbd560dd9_2026-10-07T16-40-08.005918.json,1791391033.7656484,1 +v2anneal_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc,none,0.8788888888888889,0.010881258692882334,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7d3e58f6c3_2026-10-07T16-31-53.556428.json,1791390532.036907,1 +v2anneal_merge3_116k_120k,belebele_est_Latn,5,lm-eval,vllm,,acc_norm,none,0.8788888888888889,0.010881258692882334,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7d3e58f6c3_2026-10-07T16-31-53.556428.json,1791390532.036907,1 +v2anneal_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3419fc73c7_2026-10-07T16-13-41.611048.json,1791389438.297888,1 +v2anneal_merge3_116k_120k,belebele_fin_Latn,5,lm-eval,vllm,,acc_norm,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3419fc73c7_2026-10-07T16-13-41.611048.json,1791389438.297888,1 +v2anneal_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc,none,0.9211111111111111,0.008990504946761157,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0b63d500ad_2026-10-07T16-07-27.728945.json,1791389065.6450205,1 +v2anneal_merge3_116k_120k,belebele_fra_Latn,5,lm-eval,vllm,,acc_norm,none,0.9211111111111111,0.008990504946761157,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0b63d500ad_2026-10-07T16-07-27.728945.json,1791389065.6450205,1 +v2anneal_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c70380b2be_2026-10-07T16-15-39.073333.json,1791389563.8659103,1 +v2anneal_merge3_116k_120k,belebele_hrv_Latn,5,lm-eval,vllm,,acc_norm,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c70380b2be_2026-10-07T16-15-39.073333.json,1791389563.8659103,1 +v2anneal_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc,none,0.8944444444444445,0.010247959196000194,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/81f213071e_2026-10-07T16-31-56.130300.json,1791390534.5393858,1 +v2anneal_merge3_116k_120k,belebele_hun_Latn,5,lm-eval,vllm,,acc_norm,none,0.8944444444444445,0.010247959196000194,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/81f213071e_2026-10-07T16-31-56.130300.json,1791390534.5393858,1 +v2anneal_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c55023c5f4_2026-10-07T16-48-23.287268.json,1791391522.8043396,1 +v2anneal_merge3_116k_120k,belebele_ita_Latn,5,lm-eval,vllm,,acc_norm,none,0.8922222222222222,0.010342398905593752,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c55023c5f4_2026-10-07T16-48-23.287268.json,1791391522.8043396,1 +v2anneal_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8b8e93ad86_2026-10-07T16-13-39.357109.json,1791389442.9805362,1 +v2anneal_merge3_116k_120k,belebele_lit_Latn,5,lm-eval,vllm,,acc_norm,none,0.8822222222222222,0.010750801136275996,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8b8e93ad86_2026-10-07T16-13-39.357109.json,1791389442.9805362,1 +v2anneal_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc,none,0.8988888888888888,0.010054780672527,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f68d5faf80_2026-10-07T15-38-40.174688.json,1791387350.0279233,1 +v2anneal_merge3_116k_120k,belebele_lvs_Latn,5,lm-eval,vllm,,acc_norm,none,0.8988888888888888,0.010054780672527,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f68d5faf80_2026-10-07T15-38-40.174688.json,1791387350.0279233,1 +v2anneal_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc,none,0.8733333333333333,0.011092804100207776,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/53dc912911_2026-10-07T16-31-56.974353.json,1791390538.3026342,1 +v2anneal_merge3_116k_120k,belebele_mlt_Latn,5,lm-eval,vllm,,acc_norm,none,0.8733333333333333,0.011092804100207776,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/53dc912911_2026-10-07T16-31-56.974353.json,1791390538.3026342,1 +v2anneal_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc,none,0.8855555555555555,0.010617576963634174,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6ba00d3b42_2026-10-07T16-09-20.495823.json,1791389186.802857,1 +v2anneal_merge3_116k_120k,belebele_nld_Latn,5,lm-eval,vllm,,acc_norm,none,0.8855555555555555,0.010617576963634174,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6ba00d3b42_2026-10-07T16-09-20.495823.json,1791389186.802857,1 +v2anneal_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc,none,0.8877777777777778,0.010527172059500687,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6e779a75a2_2026-10-07T16-13-29.803777.json,1791389435.8822536,1 +v2anneal_merge3_116k_120k,belebele_nob_Latn,5,lm-eval,vllm,,acc_norm,none,0.8877777777777778,0.010527172059500687,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6e779a75a2_2026-10-07T16-13-29.803777.json,1791389435.8822536,1 +v2anneal_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/577e725a1c_2026-10-07T16-13-43.611615.json,1791389440.8904984,1 +v2anneal_merge3_116k_120k,belebele_pol_Latn,5,lm-eval,vllm,,acc_norm,none,0.8911111111111111,0.010389098567166471,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/577e725a1c_2026-10-07T16-13-43.611615.json,1791389440.8904984,1 +v2anneal_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cd5a53e8d8_2026-10-07T16-07-29.321641.json,1791389071.85813,1 +v2anneal_merge3_116k_120k,belebele_por_Latn,5,lm-eval,vllm,,acc_norm,none,0.9,0.01000556018947605,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cd5a53e8d8_2026-10-07T16-07-29.321641.json,1791389071.85813,1 +v2anneal_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc,none,0.9077777777777778,0.009650009016958635,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e4939a3831_2026-10-07T16-05-36.887325.json,1791388959.1425247,1 +v2anneal_merge3_116k_120k,belebele_ron_Latn,5,lm-eval,vllm,,acc_norm,none,0.9077777777777778,0.009650009016958635,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e4939a3831_2026-10-07T16-05-36.887325.json,1791388959.1425247,1 +v2anneal_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc,none,0.8933333333333333,0.010295354033282278,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/acda8dcb98_2026-10-07T16-13-44.655182.json,1791389438.3380601,1 +v2anneal_merge3_116k_120k,belebele_slk_Latn,5,lm-eval,vllm,,acc_norm,none,0.8933333333333333,0.010295354033282278,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/acda8dcb98_2026-10-07T16-13-44.655182.json,1791389438.3380601,1 +v2anneal_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc,none,0.9055555555555556,0.009753621805733612,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f2c4383cd1_2026-10-07T16-19-51.907787.json,1791389808.918379,1 +v2anneal_merge3_116k_120k,belebele_slv_Latn,5,lm-eval,vllm,,acc_norm,none,0.9055555555555556,0.009753621805733612,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f2c4383cd1_2026-10-07T16-19-51.907787.json,1791389808.918379,1 +v2anneal_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6f17b128c3_2026-10-07T16-44-23.240363.json,1791391277.790224,1 +v2anneal_merge3_116k_120k,belebele_spa_Latn,5,lm-eval,vllm,,acc_norm,none,0.8966666666666666,0.010152099984713354,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6f17b128c3_2026-10-07T16-44-23.240363.json,1791391277.790224,1 +v2anneal_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a2fcdef03b_2026-10-07T16-21-46.263067.json,1791389925.231159,1 +v2anneal_merge3_116k_120k,belebele_swe_Latn,5,lm-eval,vllm,,acc_norm,none,0.8866666666666667,0.010572536088492642,900,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a2fcdef03b_2026-10-07T16-21-46.263067.json,1791389925.231159,1 +v2anneal_merge3_116k_120k,bigbench_cs_algorithms_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7825757575757576,0.011357814730127204,1320,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/20f884180d_2026-10-07T16-05-33.452106.json,1791388949.1726954,1 +v2anneal_merge3_116k_120k,bigbench_dyck_languages_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.625,0.015316971293620996,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f81a7ed2d5_2026-10-07T15-38-47.602678.json,1791387348.511548,1 +v2anneal_merge3_116k_120k,bigbench_language_identification_multiple_choice,10,lm-eval,vllm,,acc,none,0.2635,0.00440553241635868,10000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ee32edc5ac_2026-10-07T17-19-38.779697.json,1791389932.0014246,1 +v2anneal_merge3_116k_120k,bigbench_operators_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.8285714285714286,0.026069544122384443,210,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e5b3be67d6_2026-10-07T16-05-15.535825.json,1791388950.2509072,1 +v2anneal_merge3_116k_120k,bigbench_qa_wikidata_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.7243738005019438,0.0031345829260823275,20321,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3f2bc6af11_2026-10-07T16-41-56.652071.json,1791391026.0040138,1 +v2anneal_merge3_116k_120k,bigbench_repeat_copy_logic_generate_until,10,lm-eval,vllm,,exact_match,strict-match,0.625,0.08695104295503155,32,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2c261a91dc_2026-10-07T16-17-22.061813.json,1791389683.0468638,1 +v2anneal_merge3_116k_120k,boolq,10,lm-eval,vllm,,acc,none,0.8648318042813455,0.005979923446403381,3270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/42f63d3ca1_2026-10-07T16-14-24.468310.json,1791389318.5166333,1 +v2anneal_merge3_116k_120k,commonsense_qa,10,lm-eval,vllm,,acc,none,0.8247338247338247,0.010884940080324155,1221,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ea038fc243_2026-10-07T16-10-09.836943.json,1791389194.8193433,1 +v2anneal_merge3_116k_120k,copa,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c68eec2eb7_2026-10-07T16-11-22.116786.json,1791389323.8583083,1 +v2anneal_merge3_116k_120k,coqa,0,lm-eval,vllm,,em,none,0.7108333333333333,0.016507717337221197,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/59b8168ef6_2026-10-07T16-19-42.260341.json,1791389804.968513,1 +v2anneal_merge3_116k_120k,coqa,0,lm-eval,vllm,,f1,none,0.8283758042500975,0.011987169271551544,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/59b8168ef6_2026-10-07T16-19-42.260341.json,1791389804.968513,1 +v2anneal_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.24608205689452,0.01797026277633895,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6c6ae59ca9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-50.762785.json,1791392331.601077,1 +v2anneal_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.710181110377306,0.0038050804104300165,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6c6ae59ca9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-50.762785.json,1791392331.601077,1 +v2anneal_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2673377599045062,0.0060068567019482605,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6c6ae59ca9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-50.762785.json,1791392331.601077,1 +v2anneal_merge3_116k_120k,flores200:als_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.23386141837024,0.011979990037417624,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6c6ae59ca9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-50.762785.json,1791392331.601077,1 +v2anneal_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.00400190634043,0.019022206008794514,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6291809d26/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-38.495386.json,1791391959.686189,1 +v2anneal_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7155571624641419,0.003796945086827153,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6291809d26/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-38.495386.json,1791391959.686189,1 +v2anneal_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28476306495979353,0.006397988524376587,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6291809d26/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-38.495386.json,1791391959.686189,1 +v2anneal_merge3_116k_120k,flores200:bos_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.31199080839644,0.011759505540789049,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6291809d26/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-38.495386.json,1791391959.686189,1 +v2anneal_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,44.435381545661144,0.0173496835231321,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5629e25e27/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-44.402686.json,1791391965.275358,1 +v2anneal_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7042970655730788,0.003934595425612369,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5629e25e27/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-44.402686.json,1791391965.275358,1 +v2anneal_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2639610632468675,0.006088399199406215,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5629e25e27/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-44.402686.json,1791391965.275358,1 +v2anneal_merge3_116k_120k,flores200:bul_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.32173379718066,0.011494951903050832,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5629e25e27/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-44.402686.json,1791391965.275358,1 +v2anneal_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,49.724263301981516,0.0192390850069156,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3775f216e7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-41.297380.json,1791392202.152605,1 +v2anneal_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7375694193976121,0.003932374740931738,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3775f216e7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-41.297380.json,1791392202.152605,1 +v2anneal_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.32653106774669527,0.007035536089824123,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3775f216e7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-41.297380.json,1791392202.152605,1 +v2anneal_merge3_116k_120k,flores200:cat_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.64851319146315,0.01276545370344237,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3775f216e7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-41.297380.json,1791392202.152605,1 +v2anneal_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.15770160530729,0.017911404512516545,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/398c8222f4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-42.303763.json,1791392323.581145,1 +v2anneal_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6919021583816959,0.0041035514242660385,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/398c8222f4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-42.303763.json,1791392323.581145,1 +v2anneal_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2621988572064235,0.006314917881981893,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/398c8222f4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-42.303763.json,1791392323.581145,1 +v2anneal_merge3_116k_120k,flores200:ces_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.95822140430752,0.012416300697262047,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/398c8222f4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-42.303763.json,1791392323.581145,1 +v2anneal_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,52.139922082838325,0.019476460323116365,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/36de6eceb7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-28.360527.json,1791389849.64815,1 +v2anneal_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.752160029052037,0.003966097722376408,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/36de6eceb7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-28.360527.json,1791389849.64815,1 +v2anneal_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3533792040655075,0.0068551594467562114,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/36de6eceb7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-28.360527.json,1791389849.64815,1 +v2anneal_merge3_116k_120k,flores200:dan_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.39366166702942,0.012875066594829919,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/36de6eceb7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-28.360527.json,1791389849.64815,1 +v2anneal_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.678425397750985,0.01987298604626408,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/21d50e17cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-49.362512.json,1791392450.211879,1 +v2anneal_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7194895777338453,0.003941476234663471,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/21d50e17cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-49.362512.json,1791392450.211879,1 +v2anneal_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29142726255735113,0.0066467201998892346,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/21d50e17cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-49.362512.json,1791392450.211879,1 +v2anneal_merge3_116k_120k,flores200:deu_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.43482954270435,0.013164300385019704,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/21d50e17cd/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-49.362512.json,1791392450.211879,1 +v2anneal_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.25426427721918,0.018409509260250163,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/17d68de0ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-30.585234.json,1791391951.738993,1 +v2anneal_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6615041892817632,0.0041867303662503005,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/17d68de0ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-30.585234.json,1791391951.738993,1 +v2anneal_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22391845626261864,0.005845075034960194,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/17d68de0ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-30.585234.json,1791391951.738993,1 +v2anneal_merge3_116k_120k,flores200:ell_Grek-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.87301721991964,0.013179823304937357,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/17d68de0ea/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-30.585234.json,1791391951.738993,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu,none,34.20756226877785,0.015529523727532885,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/46ce7a71a2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-24.143268.json,1791392425.295786,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6258919519825619,0.003813705120028384,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/46ce7a71a2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-24.143268.json,1791392425.295786,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17957085610590456,0.0047971563131974215,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/46ce7a71a2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-24.143268.json,1791392425.295786,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-als_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.2436798223966,0.0107248799135216,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/46ce7a71a2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-24.143268.json,1791392425.295786,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu,none,32.410364625454086,0.017126371934401738,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/294f2183d4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-33.455730.json,1791389854.286088,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.598531180486391,0.004486900336101742,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/294f2183d4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-33.455730.json,1791389854.286088,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16782445494944437,0.004984542828155508,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/294f2183d4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-33.455730.json,1791389854.286088,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-bos_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.19808646702591,0.01177606750973415,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/294f2183d4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-33.455730.json,1791389854.286088,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu,none,40.838551219727506,0.018087700643281763,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/f58df0031b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-42.558935.json,1791392023.799792,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6601575798261174,0.003982113918194171,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/f58df0031b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-42.558935.json,1791392023.799792,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.22550451474298264,0.0054571775781439725,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/f58df0031b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-42.558935.json,1791392023.799792,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-bul_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,64.57605718892086,0.012132836123150567,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/f58df0031b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-42.558935.json,1791392023.799792,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu,none,43.96632665885944,0.018344144266881416,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3d528f31ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-20.994914.json,1791392481.807429,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6781236274577163,0.004249989645389089,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3d528f31ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-20.994914.json,1791392481.807429,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2727186401791761,0.0061914942839311465,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3d528f31ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-20.994914.json,1791392481.807429,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-cat_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.3114337830843,0.013159470331779199,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3d528f31ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-20.994914.json,1791392481.807429,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu,none,33.317942130982686,0.020173801000855245,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/29df762a45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-02-37.172660.json,1791392557.985381,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5936746023208874,0.0050053385304276625,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/29df762a45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-02-37.172660.json,1791392557.985381,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17737583099854473,0.006000514633562881,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/29df762a45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-02-37.172660.json,1791392557.985381,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ces_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.12492849832692,0.014397462001401072,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/29df762a45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-02-37.172660.json,1791392557.985381,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu,none,48.340521200116775,0.019918921877700734,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0e842d7d64/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-55-14.650193.json,1791392115.46912,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7106397520098523,0.004450212829959231,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0e842d7d64/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-55-14.650193.json,1791392115.46912,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3202718473618791,0.007171898765817588,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0e842d7d64/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-55-14.650193.json,1791392115.46912,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-dan_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.01770097324186,0.012698548239601835,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0e842d7d64/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-55-14.650193.json,1791392115.46912,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu,none,40.1440217130482,0.021557502722771814,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/ff3432d170/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-45.852702.json,1791392206.769081,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6507326230107393,0.004736259058451212,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/ff3432d170/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-45.852702.json,1791392206.769081,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23687398172630514,0.006556705375953168,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/ff3432d170/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-45.852702.json,1791392206.769081,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-deu_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.6245144822255,0.014423364713859793,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/ff3432d170/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-45.852702.json,1791392206.769081,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu,none,26.59779293372653,0.014709834136971342,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/27c3275bd3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-31.147528.json,1791389852.297667,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_1,none,0.5341500662626857,0.004485443165836674,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/27c3275bd3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-31.147528.json,1791389852.297667,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,bleu_4,none,0.12352372123726155,0.004052130136967815,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/27c3275bd3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-31.147528.json,1791389852.297667,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ell_Grek,4,lighteval,hf/accelerate,,chrf++,rescored,50.92054625554275,0.01267922512959163,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/27c3275bd3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-31.147528.json,1791389852.297667,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu,none,27.09717167469685,0.01874332834139268,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9bbd89b9ca/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-02.262569.json,1791391983.086037,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5553945983190763,0.005080049002176135,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9bbd89b9ca/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-02.262569.json,1791391983.086037,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12883734914052825,0.0053554369063597215,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9bbd89b9ca/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-02.262569.json,1791391983.086037,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-est_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.101383511441895,0.013212744233010236,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9bbd89b9ca/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-02.262569.json,1791391983.086037,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu,none,18.943625563268018,0.016345184451618894,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/547ae5cc5c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-28.424017.json,1791390029.280351,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.4847857102912023,0.004779616549389473,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/547ae5cc5c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-28.424017.json,1791390029.280351,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.07604718583127017,0.004021408879948429,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/547ae5cc5c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-28.424017.json,1791390029.280351,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-eus_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,51.89131351757798,0.01200789183326902,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/547ae5cc5c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-28.424017.json,1791390029.280351,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu,none,25.43987533334077,0.01868369804003647,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/bb0af704a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-55.540695.json,1791392216.418718,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.526765935133563,0.005158529308256972,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/bb0af704a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-55.540695.json,1791392216.418718,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11806801978963592,0.005142291709740333,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/bb0af704a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-55.540695.json,1791392216.418718,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-fin_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.479436876754725,0.012552926232970583,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/bb0af704a4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-55.540695.json,1791392216.418718,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu,none,51.30937463853825,0.02288856331091379,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e7e4a25ff4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-49.029709.json,1791391969.867488,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7035167133506295,0.004932016297177932,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e7e4a25ff4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-49.029709.json,1791391969.867488,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3664344239864,0.008030401398965324,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e7e4a25ff4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-49.029709.json,1791391969.867488,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-fra_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,70.01596957792569,0.015249776981578584,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e7e4a25ff4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-49.029709.json,1791391969.867488,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu,none,30.414469498497418,0.017970475986142244,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9e8150f63e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-00.060040.json,1791392460.884723,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.573781061619167,0.004599297919088336,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9e8150f63e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-00.060040.json,1791392460.884723,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.15638630187967953,0.0050930758173978715,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9e8150f63e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-00.060040.json,1791392460.884723,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-gle_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.24740565294167,0.01384297779772698,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9e8150f63e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-00.060040.json,1791392460.884723,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu,none,37.34873418357558,0.016100850399736067,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7167d132d0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-37.917600.json,1791389738.898731,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6407846037455855,0.00376399352820647,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7167d132d0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-37.917600.json,1791389738.898731,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20980589943611652,0.005397474902700657,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7167d132d0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-37.917600.json,1791389738.898731,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-glg_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.09615718703731,0.010969166654278306,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7167d132d0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-37.917600.json,1791389738.898731,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu,none,32.01317257055272,0.019709605746885645,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/31589ec5ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-07.460574.json,1791392468.237973,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5784680285268656,0.005000362344778175,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/31589ec5ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-07.460574.json,1791392468.237973,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1680945656588791,0.0056395219391095555,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/31589ec5ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-07.460574.json,1791392468.237973,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-hrv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.52827668020559,0.013944027086532237,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/31589ec5ce/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-07.460574.json,1791392468.237973,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu,none,26.335865917602757,0.01965728030263492,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/09f2270bb3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-35.669253.json,1791392016.858946,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5589144747190027,0.004437842716217085,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/09f2270bb3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-35.669253.json,1791392016.858946,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.11412326512075983,0.004342730018458296,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/09f2270bb3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-35.669253.json,1791392016.858946,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-hun_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.725834483042476,0.012588509717112992,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/09f2270bb3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-35.669253.json,1791392016.858946,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu,none,28.267222431228692,0.019856716777154563,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/73ac39bea4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-20.062054.json,1791392001.168064,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5392238838566209,0.004901640095321463,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/73ac39bea4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-20.062054.json,1791392001.168064,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1410592723589377,0.005389575654768672,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/73ac39bea4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-20.062054.json,1791392001.168064,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-isl_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,52.61352867761984,0.014459612615753988,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/73ac39bea4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-20.062054.json,1791392001.168064,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu,none,32.316857585602776,0.014903973023928522,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/085cb79c69/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-06.051041.json,1791391986.9006,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5935068010898633,0.0038544325893858753,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/085cb79c69/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-06.051041.json,1791391986.9006,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1630718376256354,0.004176199102514203,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/085cb79c69/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-06.051041.json,1791391986.9006,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ita_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.813265541888605,0.010338917953182775,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/085cb79c69/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-06.051041.json,1791391986.9006,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu,none,3.90543790739588,0.00749775005343413,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/b75b35ac66/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-57.140997.json,1791391917.847443,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_1,none,0.22364173444726645,0.004038918913444018,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/b75b35ac66/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-57.140997.json,1791391917.847443,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,bleu_4,none,0.006942926788583239,0.0010004892614372827,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/b75b35ac66/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-57.140997.json,1791391917.847443,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-kat_Geor,4,lighteval,hf/accelerate,,chrf++,rescored,27.14231232170085,0.009506534822636276,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/b75b35ac66/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-57.140997.json,1791391917.847443,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu,none,26.620783601232947,0.0195679168499614,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e3eab57c6c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-12.644500.json,1791390013.494495,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5433864123830364,0.0050439589875710435,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e3eab57c6c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-12.644500.json,1791390013.494495,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12358130916655434,0.0051040579858670845,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e3eab57c6c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-12.644500.json,1791390013.494495,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-lit_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.533915104935915,0.013712446164563174,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e3eab57c6c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-12.644500.json,1791390013.494495,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu,none,31.826725514212825,0.01994109894509387,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/453e0de8f1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-15.160774.json,1791389836.711436,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5936472457808123,0.005218150171716972,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/453e0de8f1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-15.160774.json,1791389836.711436,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17022564659581121,0.006297368433852077,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/453e0de8f1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-15.160774.json,1791389836.711436,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-lvs_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,57.932499094303736,0.01446387635178488,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/453e0de8f1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-15.160774.json,1791389836.711436,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu,none,35.89511741512611,0.017033150440067996,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/fd335ea7de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-28.184843.json,1791391949.178664,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6280979660790887,0.00394255922336031,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/fd335ea7de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-28.184843.json,1791391949.178664,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.1901768426746241,0.005166008698523659,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/fd335ea7de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-28.184843.json,1791391949.178664,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-mkd_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,61.74832691362179,0.011365345189662849,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/fd335ea7de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-28.184843.json,1791391949.178664,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu,none,39.71353749652156,0.01959142521554042,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6d9dd83fe0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-18-29.651253.json,1791389911.143459,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6522844423763131,0.004616518748344477,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6d9dd83fe0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-18-29.651253.json,1791389911.143459,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23589561929285172,0.006536452887513131,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6d9dd83fe0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-18-29.651253.json,1791389911.143459,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-mlt_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,66.83179322837401,0.013385049924900205,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/6d9dd83fe0/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-18-29.651253.json,1791389911.143459,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu,none,28.2522124200674,0.016280893403742416,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/032fdf993f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-50-33.068941.json,1791391834.252319,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5789511456455562,0.004336854013583433,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/032fdf993f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-50-33.068941.json,1791391834.252319,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.13143466759418232,0.004472787347921799,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/032fdf993f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-50-33.068941.json,1791391834.252319,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-nld_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.22152481516661,0.011676393996902878,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/032fdf993f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-50-33.068941.json,1791391834.252319,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu,none,34.2790171098799,0.015369406411446596,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a6e198b64c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-02.000665.json,1791391923.055371,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6130889182454841,0.003775011143866411,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a6e198b64c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-02.000665.json,1791391923.055371,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16922210310517077,0.00445225686388335,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a6e198b64c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-02.000665.json,1791391923.055371,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-nob_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.98387508852109,0.010728116985620696,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a6e198b64c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-02.000665.json,1791391923.055371,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu,none,22.427916055565554,0.016192345411359152,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0aa1f3b19e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-51.728898.json,1791391972.53533,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.49890428753801586,0.004595560044391369,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0aa1f3b19e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-51.728898.json,1791391972.53533,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.09544314093994888,0.0040460195183954,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0aa1f3b19e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-51.728898.json,1791391972.53533,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-pol_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,49.41515866159856,0.012248534261981945,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0aa1f3b19e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-51.728898.json,1791391972.53533,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu,none,49.981481989828204,0.020874321354337727,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5f4d9b619b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-36.079065.json,1791392196.932677,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7258792885275893,0.004485766611893714,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5f4d9b619b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-36.079065.json,1791392196.932677,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3374722571540004,0.007481662081633243,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5f4d9b619b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-36.079065.json,1791392196.932677,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-por_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.8702428346769,0.01362258848443635,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5f4d9b619b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-36.079065.json,1791392196.932677,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu,none,40.79539334153046,0.018769935267257596,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7aa4febae7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-29.655113.json,1791391890.463052,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6518605437485285,0.004515904950143101,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7aa4febae7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-29.655113.json,1791391890.463052,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.250750988454892,0.006345728633228352,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7aa4febae7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-29.655113.json,1791391890.463052,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ron_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.17381437108893,0.012795747225999505,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7aa4febae7/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-29.655113.json,1791391890.463052,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu,none,33.872953906420605,0.02078473504148634,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9a5d68f1de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-46.107530.json,1791392087.152957,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5950082166915677,0.005175073818329427,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9a5d68f1de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-46.107530.json,1791392087.152957,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1862219475204408,0.006144717134411454,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9a5d68f1de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-46.107530.json,1791392087.152957,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-slk_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.037796454280674,0.014475887897937842,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/9a5d68f1de/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-46.107530.json,1791392087.152957,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu,none,31.3622862914569,0.0184384795792464,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/809d3978d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-55.462523.json,1791392456.371394,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5843888072939437,0.004970480970283212,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/809d3978d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-55.462523.json,1791392456.371394,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.16808847093016793,0.005605910954469863,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/809d3978d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-55.462523.json,1791392456.371394,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-slv_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,56.20980626357084,0.013478321392202721,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/809d3978d1/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-55.462523.json,1791392456.371394,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu,none,29.44770951646516,0.0134768394569864,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/099f9103b9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-03.808743.json,1791390004.648006,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5787888185849978,0.003560436244498682,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/099f9103b9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-03.808743.json,1791390004.648006,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1407016359698028,0.003734974706300042,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/099f9103b9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-03.808743.json,1791390004.648006,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-spa_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,54.82514917710197,0.010117169219356584,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/099f9103b9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-20-03.808743.json,1791390004.648006,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu,none,34.71111563034645,0.01835930027374186,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/760ebe266a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-55-24.629782.json,1791392125.884546,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.6111971661589941,0.0047038642185904984,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/760ebe266a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-55-24.629782.json,1791392125.884546,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.19008969532845502,0.00567920142467747,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/760ebe266a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-55-24.629782.json,1791392125.884546,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-srp_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,59.07489101386495,0.012963879349574742,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/760ebe266a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-55-24.629782.json,1791392125.884546,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu,none,46.63466806448037,0.01977564249836685,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/52ce89e007/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-33.639057.json,1791391954.879426,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6939829206972801,0.004394339915996741,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/52ce89e007/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-33.639057.json,1791391954.879426,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2967256434866468,0.00680713239972519,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/52ce89e007/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-33.639057.json,1791391954.879426,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-swe_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.97563818762924,0.013233185324857793,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/52ce89e007/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-33.639057.json,1791391954.879426,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu,none,25.789390553059704,0.01939503891322125,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e84e43e126/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-39.800453.json,1791391961.24225,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5437863170911326,0.004942153552974243,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e84e43e126/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-39.800453.json,1791391961.24225,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.12115975297679976,0.005084732459504215,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e84e43e126/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-39.800453.json,1791391961.24225,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-tur_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,55.47036338968413,0.013643704767539224,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/e84e43e126/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-39.800453.json,1791391961.24225,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu,none,30.370971156638404,0.018346644302059976,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a13aa3658d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-59-50.278309.json,1791392391.081034,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_1,none,0.556346633769362,0.005006192552067589,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a13aa3658d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-59-50.278309.json,1791392391.081034,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,bleu_4,none,0.15234910337929553,0.005166479386597907,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a13aa3658d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-59-50.278309.json,1791392391.081034,1 +v2anneal_merge3_116k_120k,flores200:eng_Latn-ukr_Cyrl,4,lighteval,hf/accelerate,,chrf++,rescored,55.40289819064491,0.01346971203216983,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a13aa3658d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-59-50.278309.json,1791392391.081034,1 +v2anneal_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.23739064000617,0.01915858645920741,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/385167ac45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-00.541816.json,1791392161.657404,1 +v2anneal_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6744950279383646,0.004225699282439853,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/385167ac45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-00.541816.json,1791392161.657404,1 +v2anneal_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23340898998582935,0.006161228848293834,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/385167ac45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-00.541816.json,1791392161.657404,1 +v2anneal_merge3_116k_120k,flores200:est_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.746895516299816,0.013004296259385697,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/385167ac45/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-00.541816.json,1791392161.657404,1 +v2anneal_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.14038118795471,0.01846204982089139,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/fc4f6616c5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-37.689562.json,1791389738.749007,1 +v2anneal_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6271023961490713,0.004287881235020341,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/fc4f6616c5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-37.689562.json,1791389738.749007,1 +v2anneal_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.18389445473668753,0.005571434908377937,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/fc4f6616c5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-37.689562.json,1791389738.749007,1 +v2anneal_merge3_116k_120k,flores200:eus_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.904084867879405,0.013231411504403693,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/fc4f6616c5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-37.689562.json,1791389738.749007,1 +v2anneal_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,37.166260887610356,0.01763096463332136,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7ab98c781f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-34.321664.json,1791392315.213194,1 +v2anneal_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6543987180818834,0.00423730030980018,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7ab98c781f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-34.321664.json,1791392315.213194,1 +v2anneal_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20676863043338212,0.005815384350952322,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7ab98c781f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-34.321664.json,1791392315.213194,1 +v2anneal_merge3_116k_120k,flores200:fin_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.672541732751185,0.01248322218901932,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7ab98c781f/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-34.321664.json,1791392315.213194,1 +v2anneal_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,48.361935510681896,0.0209171717520446,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/92afc8ba1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-16-19.579388.json,1791389780.447492,1 +v2anneal_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7280315427486103,0.004332787973688452,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/92afc8ba1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-16-19.579388.json,1791389780.447492,1 +v2anneal_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.32072194803704673,0.0072099794697036475,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/92afc8ba1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-16-19.579388.json,1791389780.447492,1 +v2anneal_merge3_116k_120k,flores200:fra_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,69.46311526808479,0.014041132020783555,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/92afc8ba1d/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-16-19.579388.json,1791389780.447492,1 +v2anneal_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.68778767950702,0.020767401569527857,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/82f78a117c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-57-03.943941.json,1791392224.812832,1 +v2anneal_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7066837890258327,0.004396343068806646,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/82f78a117c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-57-03.943941.json,1791392224.812832,1 +v2anneal_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.29660015591681044,0.007195557545630336,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/82f78a117c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-57-03.943941.json,1791392224.812832,1 +v2anneal_merge3_116k_120k,flores200:gle_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.43708801949396,0.013613044981054147,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/82f78a117c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-57-03.943941.json,1791392224.812832,1 +v2anneal_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,45.1059038785664,0.01837561304526101,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5920076068/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-56.892932.json,1791392457.782833,1 +v2anneal_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7101232607660016,0.004003146238042826,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5920076068/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-56.892932.json,1791392457.782833,1 +v2anneal_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28026944551278865,0.006566115509489962,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5920076068/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-56.892932.json,1791392457.782833,1 +v2anneal_merge3_116k_120k,flores200:glg_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.09666736931158,0.011657870979207688,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5920076068/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-56.892932.json,1791392457.782833,1 +v2anneal_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.424938765655064,0.018760798241308666,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/70ade3ecec/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-34.216824.json,1791392195.068896,1 +v2anneal_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6715055496944269,0.004322081961066755,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/70ade3ecec/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-34.216824.json,1791392195.068896,1 +v2anneal_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2311427293890302,0.006075868513771612,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/70ade3ecec/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-34.216824.json,1791392195.068896,1 +v2anneal_merge3_116k_120k,flores200:hrv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.70501062683398,0.013438545150606303,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/70ade3ecec/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-34.216824.json,1791392195.068896,1 +v2anneal_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.09792014790258,0.018570950904711576,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5c5ee019a9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-12.325828.json,1791391993.889333,1 +v2anneal_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6568144880897463,0.004316839862486802,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5c5ee019a9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-12.325828.json,1791391993.889333,1 +v2anneal_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.21419218267689255,0.005947089733810765,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5c5ee019a9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-12.325828.json,1791391993.889333,1 +v2anneal_merge3_116k_120k,flores200:hun_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.134347125014635,0.013006549532562296,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/5c5ee019a9/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-12.325828.json,1791391993.889333,1 +v2anneal_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,39.22538918868871,0.019460095267291075,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0fa778536e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-43.514400.json,1791392444.466585,1 +v2anneal_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.655842508398884,0.004354326159598732,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0fa778536e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-43.514400.json,1791392444.466585,1 +v2anneal_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22569932954528094,0.006281246658895478,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0fa778536e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-43.514400.json,1791392444.466585,1 +v2anneal_merge3_116k_120k,flores200:isl_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,61.73586319489617,0.013369811455860001,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0fa778536e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-43.514400.json,1791392444.466585,1 +v2anneal_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.47745847679359,0.017081737404619424,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/eb099a4ea4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-29.356576.json,1791392070.192057,1 +v2anneal_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6517525288729812,0.0039308563209780574,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/eb099a4ea4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-29.356576.json,1791392070.192057,1 +v2anneal_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20096371608087407,0.005383790222415022,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/eb099a4ea4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-29.356576.json,1791392070.192057,1 +v2anneal_merge3_116k_120k,flores200:ita_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.219126488953115,0.011952787169925311,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/eb099a4ea4/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-29.356576.json,1791392070.192057,1 +v2anneal_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,21.35111237082976,0.017604894714389915,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0c658afc6c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-10-34.368423.json,1791393034.990218,1 +v2anneal_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.5164330022588937,0.004444044323714223,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0c658afc6c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-10-34.368423.json,1791393034.990218,1 +v2anneal_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.08769702659608251,0.003874321887415818,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0c658afc6c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-10-34.368423.json,1791393034.990218,1 +v2anneal_merge3_116k_120k,flores200:kat_Geor-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,47.66131256554475,0.013140763721903835,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/0c658afc6c/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-10-34.368423.json,1791393034.990218,1 +v2anneal_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,36.98543630619395,0.01940818816892573,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/86779b1e85/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-28.469713.json,1791392069.558536,1 +v2anneal_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6410080952834897,0.00454141424722636,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/86779b1e85/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-28.469713.json,1791392069.558536,1 +v2anneal_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.20706879656975816,0.006018169686441094,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/86779b1e85/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-28.469713.json,1791392069.558536,1 +v2anneal_merge3_116k_120k,flores200:lit_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,60.357158563791245,0.014104906876922061,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/86779b1e85/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-28.469713.json,1791392069.558536,1 +v2anneal_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.07137766792885,0.02041975249963302,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7cfec2d034/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-18-04.670265.json,1791389885.544478,1 +v2anneal_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.671779537500508,0.004419855706348593,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7cfec2d034/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-18-04.670265.json,1791389885.544478,1 +v2anneal_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.23379672412336863,0.006374113726907634,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7cfec2d034/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-18-04.670265.json,1791389885.544478,1 +v2anneal_merge3_116k_120k,flores200:lvs_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.71526825635111,0.014030905969444335,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7cfec2d034/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-18-04.670265.json,1791389885.544478,1 +v2anneal_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.43393602346372,0.018708956649795244,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/d218230b5a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-50-22.472658.json,1791391823.328819,1 +v2anneal_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7150141040379833,0.0038324727908272994,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/d218230b5a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-50-22.472658.json,1791391823.328819,1 +v2anneal_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28553227712799645,0.006242723468998546,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/d218230b5a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-50-22.472658.json,1791391823.328819,1 +v2anneal_merge3_116k_120k,flores200:mkd_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.15301769585788,0.012449934348054966,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/d218230b5a/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-50-22.472658.json,1791391823.328819,1 +v2anneal_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,58.44363394023511,0.020136465546589696,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/c067bce305/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-14.404430.json,1791391995.911472,1 +v2anneal_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7865339317008622,0.0037867868207321765,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/c067bce305/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-14.404430.json,1791391995.911472,1 +v2anneal_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.42435231472861995,0.007596104791212692,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/c067bce305/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-14.404430.json,1791391995.911472,1 +v2anneal_merge3_116k_120k,flores200:mlt_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,77.02385252714676,0.012143437551532245,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/c067bce305/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-14.404430.json,1791391995.911472,1 +v2anneal_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,34.12777906132889,0.018067890491614214,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/c91598541e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-07.184969.json,1791391928.015904,1 +v2anneal_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6198765610050009,0.004339992085245375,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/c91598541e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-07.184969.json,1791391928.015904,1 +v2anneal_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17725703822286523,0.00529550089024406,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/c91598541e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-07.184969.json,1791391928.015904,1 +v2anneal_merge3_116k_120k,flores200:nld_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.159620562798146,0.01305237801200759,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/c91598541e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-07.184969.json,1791391928.015904,1 +v2anneal_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.29291078943032,0.018942929878269208,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/45aeec96a2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-19-28.185430.json,1791389969.318843,1 +v2anneal_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7058650665158427,0.003883214608111269,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/45aeec96a2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-19-28.185430.json,1791389969.318843,1 +v2anneal_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.28664735826866367,0.006254674451423709,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/45aeec96a2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-19-28.185430.json,1791389969.318843,1 +v2anneal_merge3_116k_120k,flores200:nob_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,67.72319720294796,0.012475019032160205,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/45aeec96a2/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-19-28.185430.json,1791389969.318843,1 +v2anneal_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.098265306432324,0.01751056859397474,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3268d13c2b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-51.389882.json,1791392452.232751,1 +v2anneal_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6177839101327308,0.00421874931325777,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3268d13c2b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-51.389882.json,1791392452.232751,1 +v2anneal_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.1690265476027303,0.005001482856862107,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3268d13c2b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-51.389882.json,1791392452.232751,1 +v2anneal_merge3_116k_120k,flores200:pol_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,58.18298762984029,0.012569162133353502,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/3268d13c2b/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-00-51.389882.json,1791392452.232751,1 +v2anneal_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,51.88439356809378,0.019177183632011204,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/51466a1289/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-34.672761.json,1791392495.775331,1 +v2anneal_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7517989966949831,0.004009665268915154,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/51466a1289/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-34.672761.json,1791392495.775331,1 +v2anneal_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.3529134888532663,0.007130019825578983,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/51466a1289/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-34.672761.json,1791392495.775331,1 +v2anneal_merge3_116k_120k,flores200:por_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,72.3241777794251,0.01289011262528804,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/51466a1289/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T17-01-34.672761.json,1791392495.775331,1 +v2anneal_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.57667277074009,0.020001091772912608,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/b6eff196e8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-56.740850.json,1791392097.584799,1 +v2anneal_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.718844979599317,0.004097496862543597,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/b6eff196e8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-56.740850.json,1791392097.584799,1 +v2anneal_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2974444626232718,0.006687818509573176,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/b6eff196e8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-56.740850.json,1791392097.584799,1 +v2anneal_merge3_116k_120k,flores200:ron_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.96900080363774,0.013059858327925148,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/b6eff196e8/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-56.740850.json,1791392097.584799,1 +v2anneal_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,42.34751557022917,0.019991354313412667,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/122c7639be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-29.165216.json,1791392190.006145,1 +v2anneal_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.68665527169826,0.004266405425327781,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/122c7639be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-29.165216.json,1791392190.006145,1 +v2anneal_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2518994392115335,0.006553809991662521,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/122c7639be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-29.165216.json,1791392190.006145,1 +v2anneal_merge3_116k_120k,flores200:slk_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.6762617703593,0.01324820091677549,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/122c7639be/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-56-29.165216.json,1791392190.006145,1 +v2anneal_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,38.77800600079532,0.01873591569548012,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7b0042d81e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-59.469507.json,1791391920.947124,1 +v2anneal_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6633759369899623,0.0041926540629264935,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7b0042d81e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-59.469507.json,1791391920.947124,1 +v2anneal_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.22015795954753134,0.005866062393310757,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7b0042d81e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-59.469507.json,1791391920.947124,1 +v2anneal_merge3_116k_120k,flores200:slv_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,62.384913687178326,0.013069203196787504,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7b0042d81e/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-51-59.469507.json,1791391920.947124,1 +v2anneal_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,33.31176109387994,0.02093847176883282,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a6693089d5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-02.353514.json,1791391983.15954,1 +v2anneal_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6315516643036957,0.0040444242876826455,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a6693089d5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-02.353514.json,1791391983.15954,1 +v2anneal_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.17830863367087246,0.0051000715025016075,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a6693089d5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-02.353514.json,1791391983.15954,1 +v2anneal_merge3_116k_120k,flores200:spa_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,59.989345795175055,0.012505104979333354,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/a6693089d5/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-53-02.353514.json,1791391983.15954,1 +v2anneal_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,46.73776967789094,0.01902985797563919,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/8474872503/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-57.192941.json,1791389757.989459,1 +v2anneal_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7192684462950446,0.003993207003928523,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/8474872503/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-57.192941.json,1791389757.989459,1 +v2anneal_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2971397928685469,0.006610612326343375,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/8474872503/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-57.192941.json,1791389757.989459,1 +v2anneal_merge3_116k_120k,flores200:srp_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,68.88619849344417,0.012192894733673413,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/8474872503/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-15-57.192941.json,1791389757.989459,1 +v2anneal_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,51.24497868040627,0.018667245261616783,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/ba70802617/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-04.062983.json,1791391924.867519,1 +v2anneal_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.7438086467078101,0.0038277932723396494,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/ba70802617/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-04.062983.json,1791391924.867519,1 +v2anneal_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.33784420060665155,0.006830947902013069,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/ba70802617/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-04.062983.json,1791391924.867519,1 +v2anneal_merge3_116k_120k,flores200:swe_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,71.23132427329155,0.012283127676032542,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/ba70802617/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-52-04.062983.json,1791391924.867519,1 +v2anneal_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,40.32705701049744,0.018905289854083036,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7e3ee19658/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-49.643999.json,1791392330.53517,1 +v2anneal_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.673989641452701,0.0042778308814906876,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7e3ee19658/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-49.643999.json,1791392330.53517,1 +v2anneal_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2358899768912726,0.006293673776930906,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7e3ee19658/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-49.643999.json,1791392330.53517,1 +v2anneal_merge3_116k_120k,flores200:tur_Latn-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,63.588129667834025,0.013546413149901996,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/7e3ee19658/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-58-49.643999.json,1791392330.53517,1 +v2anneal_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu,none,43.09651388540951,0.01881534832408428,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/2f00373aaf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-37.778380.json,1791389859.385491,1 +v2anneal_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_1,none,0.6920110092166485,0.004149007961586074,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/2f00373aaf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-37.778380.json,1791389859.385491,1 +v2anneal_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,bleu_4,none,0.2587202201806801,0.006325914239133573,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/2f00373aaf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-37.778380.json,1791389859.385491,1 +v2anneal_merge3_116k_120k,flores200:ukr_Cyrl-eng_Latn,4,lighteval,hf/accelerate,,chrf++,rescored,65.61826583021076,0.012904704048890013,1012,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/2f00373aaf/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-17-37.778380.json,1791389859.385491,1 +v2anneal_merge3_116k_120k,global_mgsm_ca,5,lm-eval,vllm,,exact_match,flexible-extract,0.368,0.03056207062099316,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/790910f9f7_2026-10-07T16-05-16.175092.json,1791388949.7246637,1 +v2anneal_merge3_116k_120k,global_mgsm_cs,5,lm-eval,vllm,,exact_match,flexible-extract,0.328,0.02975239182447539,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/602b717ec3_2026-10-07T16-46-17.128802.json,1791391405.4850373,1 +v2anneal_merge3_116k_120k,global_mgsm_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.336,0.029933259094191516,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d48d2e97b8_2026-10-07T16-31-49.907996.json,1791390539.534878,1 +v2anneal_merge3_116k_120k,global_mgsm_el,5,lm-eval,vllm,,exact_match,flexible-extract,0.356,0.03034368065715322,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c4ed962b44_2026-10-07T16-28-11.279068.json,1791390300.5016441,1 +v2anneal_merge3_116k_120k,global_mgsm_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.344,0.03010450339231639,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/375199231f_2026-10-07T16-33-44.202033.json,1791390656.3693807,1 +v2anneal_merge3_116k_120k,global_mgsm_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.372,0.03063032594455832,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ea5b3b5cdb_2026-10-07T16-31-36.555325.json,1791390529.9215274,1 +v2anneal_merge3_116k_120k,global_mgsm_eu,5,lm-eval,vllm,,exact_match,flexible-extract,0.3,0.029040893477575856,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/88e4f9480e_2026-10-07T16-11-29.037419.json,1791389323.098271,1 +v2anneal_merge3_116k_120k,global_mgsm_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.324,0.029658294924545574,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a2a2149566_2026-10-07T16-13-30.433688.json,1791389440.8908067,1 +v2anneal_merge3_116k_120k,global_mgsm_gl,5,lm-eval,vllm,,exact_match,flexible-extract,0.36,0.030418764025175002,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f0f5cf673d_2026-10-07T16-07-22.267819.json,1791389077.0807314,1 +v2anneal_merge3_116k_120k,global_mgsm_hu,5,lm-eval,vllm,,exact_match,flexible-extract,0.284,0.028576958730437405,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/784f5d7778_2026-10-07T16-11-23.852537.json,1791389316.6157012,1 +v2anneal_merge3_116k_120k,global_mgsm_sr,5,lm-eval,vllm,,exact_match,flexible-extract,0.356,0.03034368065715322,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0b560d608a_2026-10-07T16-11-24.630853.json,1791389316.0418627,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs,5,lm-eval,vllm,yes,acc,none,0.6694203104970802,0.003751727485172471,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_abstract_algebra,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_anatomy,5,lm-eval,vllm,,acc,none,0.5925925925925926,0.042446332383532265,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_astronomy,5,lm-eval,vllm,,acc,none,0.7631578947368421,0.03459777606810534,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7169811320754716,0.027724236492700883,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_college_biology,5,lm-eval,vllm,,acc,none,0.8263888888888888,0.03167473383795719,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_college_medicine,5,lm-eval,vllm,,acc,none,0.6820809248554913,0.0355068398916558,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7574468085106383,0.02802022627120023,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6551724137931034,0.03960933549451213,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6587301587301587,0.024419234966819043,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_formal_logic,5,lm-eval,vllm,,acc,none,0.5952380952380952,0.043902592653775656,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_global_facts,5,lm-eval,vllm,,acc,none,0.37,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_biology,5,lm-eval,vllm,,acc,none,0.8129032258064516,0.02218571009225229,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.625615763546798,0.03405155380561957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_geography,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026552207828215258,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8808290155440415,0.02338193534812143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7307692307692307,0.022489389793654804,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.43333333333333335,0.030213340289238,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7857142857142857,0.026653531596715505,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_physics,5,lm-eval,vllm,,acc,none,0.5165562913907285,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8642201834862385,0.014686907556339952,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.031919234456861886,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8088235294117647,0.02759917430064072,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8607594936708861,0.022535526352692684,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_human_aging,5,lm-eval,vllm,,acc,none,0.7488789237668162,0.029105220833224605,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_human_sexuality,5,lm-eval,vllm,,acc,none,0.816793893129771,0.03392770926494735,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_humanities,5,lm-eval,vllm,yes,acc,none,0.5957492029755579,0.006650728779894067,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_international_law,5,lm-eval,vllm,,acc,none,0.859504132231405,0.03172233426002156,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7055214723926381,0.03581165790474083,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_machine_learning,5,lm-eval,vllm,,acc,none,0.5982142857142857,0.04653333146973646,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_marketing,5,lm-eval,vllm,,acc,none,0.8504273504273504,0.023365051491753757,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_miscellaneous,5,lm-eval,vllm,,acc,none,0.776500638569604,0.014897235229450705,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_moral_disputes,5,lm-eval,vllm,,acc,none,0.7167630057803468,0.024257901705323326,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_moral_scenarios,5,lm-eval,vllm,,acc,none,0.32625698324022345,0.01568044151888927,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_nutrition,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.023805186524888222,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_other,5,lm-eval,vllm,yes,acc,none,0.700032185387834,0.007936545811359861,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_prehistory,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.023132376234543416,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_professional_accounting,5,lm-eval,vllm,,acc,none,0.4645390070921986,0.029752389657427127,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_professional_law,5,lm-eval,vllm,,acc,none,0.49934810951760106,0.012770225252255563,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_professional_medicine,5,lm-eval,vllm,,acc,none,0.6911764705882353,0.028064998167040053,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_professional_psychology,5,lm-eval,vllm,,acc,none,0.6977124183006536,0.018579232711113967,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_security_studies,5,lm-eval,vllm,,acc,none,0.7591836734693878,0.027372942201788125,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7754306142346441,0.007367241884026713,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_stem,5,lm-eval,vllm,yes,acc,none,0.6457342213764669,0.008235783042698307,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_cs_world_religions,5,lm-eval,vllm,,acc,none,0.8304093567251462,0.02878210810540169,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9a6591a646_2026-10-07T16-15-50.494389.json,1791389435.8022108,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de,5,lm-eval,vllm,yes,acc,none,0.6712718985899444,0.003755566164758963,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_abstract_algebra,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_anatomy,5,lm-eval,vllm,,acc,none,0.5777777777777777,0.042667634040995855,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_business_ethics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7169811320754716,0.027724236492700883,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_college_chemistry,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_college_computer_science,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7404255319148936,0.02865917937429237,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6482758620689655,0.03979236637497416,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6084656084656085,0.025138091388851137,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_formal_logic,5,lm-eval,vllm,,acc,none,0.626984126984127,0.043255060420170875,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_global_facts,5,lm-eval,vllm,,acc,none,0.36,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_biology,5,lm-eval,vllm,,acc,none,0.8258064516129032,0.02157624818451461,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6305418719211823,0.03395970381998578,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8242424242424242,0.029720943006224455,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_geography,5,lm-eval,vllm,,acc,none,0.8535353535353535,0.025190921114603887,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.917098445595855,0.019899341315721786,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7435897435897436,0.022139081103971635,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8235294117647058,0.024762902678057915,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_physics,5,lm-eval,vllm,,acc,none,0.5231788079470199,0.04078093859163086,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8440366972477065,0.015555802713590066,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6388888888888888,0.03275773486101003,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8227848101265823,0.024856364184503203,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_human_aging,5,lm-eval,vllm,,acc,none,0.6771300448430493,0.031381476375754995,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_human_sexuality,5,lm-eval,vllm,,acc,none,0.816793893129771,0.03392770926494735,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_humanities,5,lm-eval,vllm,yes,acc,none,0.5982996811902231,0.006677084589972105,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_international_law,5,lm-eval,vllm,,acc,none,0.7851239669421488,0.037494924487096966,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_jurisprudence,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.04330043749650743,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7484662576687117,0.03408997886857529,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_machine_learning,5,lm-eval,vllm,,acc,none,0.5535714285714286,0.04718471485219583,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_management,5,lm-eval,vllm,,acc,none,0.8058252427184466,0.03916667762822582,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_marketing,5,lm-eval,vllm,,acc,none,0.8760683760683761,0.021586494001281407,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_miscellaneous,5,lm-eval,vllm,,acc,none,0.7956577266922095,0.014419123980931954,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3474860335195531,0.015925564060208213,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_nutrition,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.024848018263875137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_other,5,lm-eval,vllm,yes,acc,none,0.7064692629546186,0.007881187327101052,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_philosophy,5,lm-eval,vllm,,acc,none,0.7459807073954984,0.024723861504771655,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_prehistory,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.02277971908873342,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_professional_accounting,5,lm-eval,vllm,,acc,none,0.4716312056737589,0.029779450957303062,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_professional_law,5,lm-eval,vllm,,acc,none,0.49022164276401564,0.012767793787729296,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_professional_medicine,5,lm-eval,vllm,,acc,none,0.6948529411764706,0.02797154137017067,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_professional_psychology,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.01843342764940195,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_security_studies,5,lm-eval,vllm,,acc,none,0.726530612244898,0.028535560337128486,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_social_sciences,5,lm-eval,vllm,yes,acc,none,0.780630484237894,0.007332394036416054,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_sociology,5,lm-eval,vllm,,acc,none,0.845771144278607,0.025538433368578303,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_stem,5,lm-eval,vllm,yes,acc,none,0.6387567396130669,0.008304025429916628,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_virology,5,lm-eval,vllm,,acc,none,0.536144578313253,0.038823108508905954,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_de_world_religions,5,lm-eval,vllm,,acc,none,0.8128654970760234,0.029913127232368063,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79a1c2cd10_2026-10-07T16-36-42.150234.json,1791390658.4263988,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el,5,lm-eval,vllm,yes,acc,none,0.6509756444950862,0.0038386281266921973,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_abstract_algebra,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_anatomy,5,lm-eval,vllm,,acc,none,0.562962962962963,0.042849586397534056,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_astronomy,5,lm-eval,vllm,,acc,none,0.75,0.03523807393012047,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_business_ethics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7018867924528301,0.028152837942493784,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_college_biology,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03942082639927217,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_college_computer_science,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_computer_security,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7404255319148936,0.02865917937429237,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6689655172413793,0.03921545312467122,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.02487081525105711,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_global_facts,5,lm-eval,vllm,,acc,none,0.35,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_biology,5,lm-eval,vllm,,acc,none,0.8129032258064516,0.02218571009225229,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.034139638059062394,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_european_history,5,lm-eval,vllm,,acc,none,0.793939393939394,0.03158415324047706,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_geography,5,lm-eval,vllm,,acc,none,0.8080808080808081,0.028057791672989062,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8860103626943006,0.022935144053919394,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7435897435897436,0.022139081103971635,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.42592592592592593,0.0301491356013659,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7983193277310925,0.026064313406304485,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_physics,5,lm-eval,vllm,,acc,none,0.5099337748344371,0.040816771072484305,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8018348623853211,0.017090573804217808,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6712962962962963,0.03203614084670054,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_us_history,5,lm-eval,vllm,,acc,none,0.803921568627451,0.027865942286639318,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_human_aging,5,lm-eval,vllm,,acc,none,0.6995515695067265,0.030769352008229164,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_human_sexuality,5,lm-eval,vllm,,acc,none,0.7786259541984732,0.036412970813137276,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_humanities,5,lm-eval,vllm,yes,acc,none,0.5893730074388948,0.006731994238048544,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_jurisprudence,5,lm-eval,vllm,,acc,none,0.7685185185185185,0.040774947092526284,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6932515337423313,0.036230899157241474,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_machine_learning,5,lm-eval,vllm,,acc,none,0.5267857142857143,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_marketing,5,lm-eval,vllm,,acc,none,0.8418803418803419,0.02390232554956044,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_medical_genetics,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_miscellaneous,5,lm-eval,vllm,,acc,none,0.70242656449553,0.01634911191290953,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_moral_disputes,5,lm-eval,vllm,,acc,none,0.7427745664739884,0.02353292543104432,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3418994413407821,0.01586450646160461,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_nutrition,5,lm-eval,vllm,,acc,none,0.7189542483660131,0.025738854797818695,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_other,5,lm-eval,vllm,yes,acc,none,0.660122304473769,0.008261777367058921,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_philosophy,5,lm-eval,vllm,,acc,none,0.729903536977492,0.02521804037341055,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_prehistory,5,lm-eval,vllm,,acc,none,0.7160493827160493,0.02508947852376511,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_professional_accounting,5,lm-eval,vllm,,acc,none,0.4432624113475177,0.02963483847376595,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_professional_law,5,lm-eval,vllm,,acc,none,0.49282920469361147,0.012768922739553434,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_professional_medicine,5,lm-eval,vllm,,acc,none,0.6360294117647058,0.029227192460031966,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_professional_psychology,5,lm-eval,vllm,,acc,none,0.6895424836601307,0.018718067052623143,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7611309717257069,0.007568276210360626,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_stem,5,lm-eval,vllm,yes,acc,none,0.6263875673961307,0.008397394129228297,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_virology,5,lm-eval,vllm,,acc,none,0.4759036144578313,0.03887971849597268,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_el_world_religions,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.03126781714663182,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1e290b628_2026-10-07T16-27-26.975518.json,1791390054.6249633,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en,5,lm-eval,vllm,yes,acc,none,0.7271044010824669,0.0035987747327948963,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_abstract_algebra,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_anatomy,5,lm-eval,vllm,,acc,none,0.6148148148148148,0.042039210401562783,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_business_ethics,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7622641509433963,0.026199808807561956,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_college_biology,5,lm-eval,vllm,,acc,none,0.8680555555555556,0.02830096838204442,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_college_chemistry,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_college_computer_science,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_computer_security,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_conceptual_physics,5,lm-eval,vllm,,acc,none,0.8,0.02614881801842454,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_econometrics,5,lm-eval,vllm,,acc,none,0.5877192982456141,0.046306532033665936,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7586206896551724,0.035659981741353035,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.02467786284133279,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_formal_logic,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.04285714285714286,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_global_facts,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_biology,5,lm-eval,vllm,,acc,none,0.8741935483870967,0.018865834288030025,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6847290640394089,0.03269080871970192,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_geography,5,lm-eval,vllm,,acc,none,0.8888888888888888,0.02239078763821682,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9585492227979274,0.01438543285747641,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7846153846153846,0.02084303455746285,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5222222222222223,0.030455413985678415,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8739495798319328,0.021559623121213883,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_physics,5,lm-eval,vllm,,acc,none,0.5761589403973509,0.040348466786033946,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_psychology,5,lm-eval,vllm,,acc,none,0.9100917431192661,0.012264304540230489,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.0314155462940254,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8676470588235294,0.02378429752091887,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_high_school_world_history,5,lm-eval,vllm,,acc,none,0.890295358649789,0.02034340073486879,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_human_aging,5,lm-eval,vllm,,acc,none,0.7802690582959642,0.027790177064383567,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_human_sexuality,5,lm-eval,vllm,,acc,none,0.8396946564885496,0.032178294207446285,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_humanities,5,lm-eval,vllm,yes,acc,none,0.6811902231668437,0.006511012815565862,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_jurisprudence,5,lm-eval,vllm,,acc,none,0.8148148148148148,0.03755265865037181,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_logical_fallacies,5,lm-eval,vllm,,acc,none,0.803680981595092,0.031207970394709197,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_machine_learning,5,lm-eval,vllm,,acc,none,0.5982142857142857,0.04653333146973646,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_marketing,5,lm-eval,vllm,,acc,none,0.8846153846153846,0.0209301931851793,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_medical_genetics,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_miscellaneous,5,lm-eval,vllm,,acc,none,0.8275862068965517,0.013507943909371756,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_moral_disputes,5,lm-eval,vllm,,acc,none,0.7976878612716763,0.021628077380196193,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_moral_scenarios,5,lm-eval,vllm,,acc,none,0.5396648044692738,0.016669799592112056,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_nutrition,5,lm-eval,vllm,,acc,none,0.7712418300653595,0.02405102973991231,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_other,5,lm-eval,vllm,yes,acc,none,0.7428387512069521,0.007608068594874519,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_philosophy,5,lm-eval,vllm,,acc,none,0.7620578778135049,0.02418515064781868,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_prehistory,5,lm-eval,vllm,,acc,none,0.845679012345679,0.02010083099985096,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_professional_accounting,5,lm-eval,vllm,,acc,none,0.5354609929078015,0.02975238965742713,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_professional_law,5,lm-eval,vllm,,acc,none,0.5658409387222947,0.012659033237067257,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_professional_medicine,5,lm-eval,vllm,,acc,none,0.7279411764705882,0.027033041151681442,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_professional_psychology,5,lm-eval,vllm,,acc,none,0.7532679738562091,0.017440820367402566,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_public_relations,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.04350271442923247,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8267793305167371,0.006664239567494516,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_sociology,5,lm-eval,vllm,,acc,none,0.8756218905472637,0.023335401790166316,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_stem,5,lm-eval,vllm,yes,acc,none,0.6828417380272757,0.007998442059099428,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_virology,5,lm-eval,vllm,,acc,none,0.5421686746987951,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_en_world_religions,5,lm-eval,vllm,,acc,none,0.8187134502923976,0.02954774168764006,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fbeb4baa1c_2026-10-07T16-26-17.054280.json,1791390049.1894133,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es,5,lm-eval,vllm,yes,acc,none,0.6874376869391825,0.0037319036848674244,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_anatomy,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.04292596718256977,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6981132075471698,0.028254200344438735,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_college_biology,5,lm-eval,vllm,,acc,none,0.8125,0.032639560491693344,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_college_chemistry,5,lm-eval,vllm,,acc,none,0.55,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_college_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_college_medicine,5,lm-eval,vllm,,acc,none,0.6820809248554913,0.0355068398916558,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_college_physics,5,lm-eval,vllm,,acc,none,0.5,0.04975185951049946,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_computer_security,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7404255319148936,0.02865917937429237,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_econometrics,5,lm-eval,vllm,,acc,none,0.6052631578947368,0.04598188057816546,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6827586206896552,0.03878352372138618,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6455026455026455,0.024636830602842035,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_global_facts,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_biology,5,lm-eval,vllm,,acc,none,0.8516129032258064,0.02022273755433042,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6748768472906403,0.03295797566311267,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_geography,5,lm-eval,vllm,,acc,none,0.8434343434343434,0.025890520358141458,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8808290155440415,0.02338193534812143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.782051282051282,0.020932445774463234,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4888888888888889,0.030478009819615792,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8277310924369747,0.024528664971305403,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_physics,5,lm-eval,vllm,,acc,none,0.5562913907284768,0.04056527902281736,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8697247706422019,0.01443186285247314,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8607594936708861,0.022535526352692684,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_human_aging,5,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_human_sexuality,5,lm-eval,vllm,,acc,none,0.8015267175572519,0.034981493854624734,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_humanities,5,lm-eval,vllm,yes,acc,none,0.6208289054197662,0.006690212610045217,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_jurisprudence,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.044531975073749855,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7300613496932515,0.034878251684978955,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_machine_learning,5,lm-eval,vllm,,acc,none,0.5625,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_management,5,lm-eval,vllm,,acc,none,0.7669902912621359,0.041858325989283136,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_marketing,5,lm-eval,vllm,,acc,none,0.8717948717948718,0.021901905115073377,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_miscellaneous,5,lm-eval,vllm,,acc,none,0.7994891443167306,0.01431765370859427,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_moral_disputes,5,lm-eval,vllm,,acc,none,0.7601156069364162,0.02298959254312351,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_moral_scenarios,5,lm-eval,vllm,,acc,none,0.41787709497206704,0.01649540063582002,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_nutrition,5,lm-eval,vllm,,acc,none,0.7287581699346405,0.025457756696667815,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_other,5,lm-eval,vllm,yes,acc,none,0.704216285806244,0.007939453883817244,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_philosophy,5,lm-eval,vllm,,acc,none,0.7491961414790996,0.024619771956697113,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_prehistory,5,lm-eval,vllm,,acc,none,0.7592592592592593,0.0237885835516586,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_professional_accounting,5,lm-eval,vllm,,acc,none,0.5035460992907801,0.029826749153280853,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_professional_law,5,lm-eval,vllm,,acc,none,0.5078226857887875,0.012768673076111898,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_professional_medicine,5,lm-eval,vllm,,acc,none,0.6691176470588235,0.028582709753898396,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_professional_psychology,5,lm-eval,vllm,,acc,none,0.7352941176470589,0.01784808957491327,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_public_relations,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.04350271442923247,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7981800454988626,0.0071515372543410425,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_stem,5,lm-eval,vllm,yes,acc,none,0.6622264509990485,0.008163769434710793,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_virology,5,lm-eval,vllm,,acc,none,0.5301204819277109,0.03885425420866771,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_es_world_religions,5,lm-eval,vllm,,acc,none,0.847953216374269,0.027539122889061483,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c72c5fb038_2026-10-07T16-14-31.372139.json,1791389317.761178,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr,5,lm-eval,vllm,yes,acc,none,0.681241988320752,0.0037324312469892923,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_anatomy,5,lm-eval,vllm,,acc,none,0.6,0.0423207369515159,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7396226415094339,0.027008766090708045,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_college_computer_science,5,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_college_mathematics,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_college_medicine,5,lm-eval,vllm,,acc,none,0.7052023121387283,0.03476599607516476,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_computer_security,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7702127659574468,0.0275017529444124,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_econometrics,5,lm-eval,vllm,,acc,none,0.5350877192982456,0.04692008381368906,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.696551724137931,0.03831226048850335,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6375661375661376,0.024757473902752066,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_formal_logic,5,lm-eval,vllm,,acc,none,0.5952380952380952,0.043902592653775656,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8354838709677419,0.021090847745939306,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.625615763546798,0.03405155380561957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_geography,5,lm-eval,vllm,,acc,none,0.8080808080808081,0.028057791672989062,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8911917098445595,0.02247325333276875,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7333333333333333,0.022421273612923794,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5894039735099338,0.04016689594849927,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8440366972477065,0.015555802713590066,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6574074074074074,0.0323658525260216,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.024857478080250486,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.869198312236287,0.02194876605947081,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_human_aging,5,lm-eval,vllm,,acc,none,0.7130044843049327,0.030360379710291947,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_human_sexuality,5,lm-eval,vllm,,acc,none,0.816793893129771,0.03392770926494735,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_humanities,5,lm-eval,vllm,yes,acc,none,0.6172157279489905,0.006588788081739653,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_international_law,5,lm-eval,vllm,,acc,none,0.8842975206611571,0.029199802455622825,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7777777777777778,0.04019107472557348,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7177914110429447,0.03536117886664741,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_machine_learning,5,lm-eval,vllm,,acc,none,0.5178571428571429,0.047427623612430116,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_management,5,lm-eval,vllm,,acc,none,0.8058252427184466,0.03916667762822582,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_marketing,5,lm-eval,vllm,,acc,none,0.8717948717948718,0.021901905115073377,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_miscellaneous,5,lm-eval,vllm,,acc,none,0.8045977011494253,0.014179171373424396,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7803468208092486,0.022289638852617966,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.36201117318435755,0.016073067350152966,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_nutrition,5,lm-eval,vllm,,acc,none,0.7581699346405228,0.024518195641879306,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_other,5,lm-eval,vllm,yes,acc,none,0.7167685870614741,0.007822142232758877,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_philosophy,5,lm-eval,vllm,,acc,none,0.752411575562701,0.024513879973621984,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_prehistory,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.02277971908873342,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_professional_accounting,5,lm-eval,vllm,,acc,none,0.4858156028368794,0.029815494483682023,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_professional_law,5,lm-eval,vllm,,acc,none,0.5104302477183833,0.012767457253930452,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_professional_medicine,5,lm-eval,vllm,,acc,none,0.7205882352941176,0.02725720260611497,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_professional_psychology,5,lm-eval,vllm,,acc,none,0.696078431372549,0.018607552131279893,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_public_relations,5,lm-eval,vllm,,acc,none,0.7,0.04389311454644288,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_security_studies,5,lm-eval,vllm,,acc,none,0.7673469387755102,0.02704925791589615,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7738056548586285,0.007423695539267913,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_sociology,5,lm-eval,vllm,,acc,none,0.835820895522388,0.026193923544454094,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_stem,5,lm-eval,vllm,yes,acc,none,0.6514430700919759,0.008230863862084171,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_virology,5,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_fr_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/877a591293_2026-10-07T16-16-58.212851.json,1791389452.8537238,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it,5,lm-eval,vllm,yes,acc,none,0.6820965674405355,0.003757694185316575,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_abstract_algebra,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7056603773584905,0.028049186315695293,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_college_biology,5,lm-eval,vllm,,acc,none,0.7847222222222222,0.034370793441061386,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_college_computer_science,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_college_medicine,5,lm-eval,vllm,,acc,none,0.6705202312138728,0.03583901754736415,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_college_physics,5,lm-eval,vllm,,acc,none,0.5490196078431373,0.04951218252396262,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_computer_security,5,lm-eval,vllm,,acc,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_conceptual_physics,5,lm-eval,vllm,,acc,none,0.774468085106383,0.02732107841738755,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_econometrics,5,lm-eval,vllm,,acc,none,0.543859649122807,0.04685473041907789,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7103448275862069,0.03780019230438011,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6534391534391535,0.024508777521028414,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_formal_logic,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.04285714285714286,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_global_facts,5,lm-eval,vllm,,acc,none,0.46,0.05009082659620332,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_biology,5,lm-eval,vllm,,acc,none,0.8516129032258064,0.02022273755433042,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6403940886699507,0.0337645824650957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7818181818181819,0.032250781083062896,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_geography,5,lm-eval,vllm,,acc,none,0.8636363636363636,0.02445015597318985,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.735897435897436,0.02235219373745328,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8151260504201681,0.025215992877954195,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_physics,5,lm-eval,vllm,,acc,none,0.5496688741721855,0.04062290018683777,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8623853211009175,0.014770105878649499,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6574074074074074,0.0323658525260216,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8431372549019608,0.02552472232455332,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8270042194092827,0.024621562866768382,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_human_aging,5,lm-eval,vllm,,acc,none,0.6995515695067265,0.030769352008229164,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_humanities,5,lm-eval,vllm,yes,acc,none,0.6187035069075452,0.006709309626758657,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_jurisprudence,5,lm-eval,vllm,,acc,none,0.7407407407407407,0.04236511258094632,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7607361963190185,0.033519538795212675,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_machine_learning,5,lm-eval,vllm,,acc,none,0.5803571428571429,0.04684099321077108,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_marketing,5,lm-eval,vllm,,acc,none,0.8418803418803419,0.02390232554956044,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_miscellaneous,5,lm-eval,vllm,,acc,none,0.7841634738186463,0.01471168438613984,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4245810055865922,0.016531170993278946,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_nutrition,5,lm-eval,vllm,,acc,none,0.7287581699346405,0.025457756696667815,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_other,5,lm-eval,vllm,yes,acc,none,0.6948825233344061,0.008040700091750777,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_philosophy,5,lm-eval,vllm,,acc,none,0.7363344051446945,0.02502553850053229,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_prehistory,5,lm-eval,vllm,,acc,none,0.7654320987654321,0.0235768817440057,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_professional_accounting,5,lm-eval,vllm,,acc,none,0.48226950354609927,0.02980873964223769,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_professional_law,5,lm-eval,vllm,,acc,none,0.5,0.012770236105969923,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_professional_medicine,5,lm-eval,vllm,,acc,none,0.6580882352941176,0.02881472242225415,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_professional_psychology,5,lm-eval,vllm,,acc,none,0.7091503267973857,0.018373116915903997,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_security_studies,5,lm-eval,vllm,,acc,none,0.746938775510204,0.027833023871399704,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7848553786155346,0.007264140219326905,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_sociology,5,lm-eval,vllm,,acc,none,0.8706467661691543,0.02372983088101855,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_stem,5,lm-eval,vllm,yes,acc,none,0.6638122423089121,0.008172573503350525,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_it_world_religions,5,lm-eval,vllm,,acc,none,0.8245614035087719,0.0291708855007277,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a44e0eef79_2026-10-07T16-38-51.513838.json,1791390782.5673332,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt,5,lm-eval,vllm,yes,acc,none,0.6457057399230879,0.0038217708255745475,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_anatomy,5,lm-eval,vllm,,acc,none,0.5555555555555556,0.04292596718256977,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_astronomy,5,lm-eval,vllm,,acc,none,0.7960526315789473,0.03279000406310049,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_business_ethics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_college_biology,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.037455547914624555,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_college_chemistry,5,lm-eval,vllm,,acc,none,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_college_computer_science,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_college_mathematics,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_college_medicine,5,lm-eval,vllm,,acc,none,0.653179190751445,0.03629146670159661,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_computer_security,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7361702127659574,0.028809989854102946,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_econometrics,5,lm-eval,vllm,,acc,none,0.4824561403508772,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.040434618619167494,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.02467786284133279,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8225806451612904,0.021732540689329255,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6157635467980296,0.03422398565657553,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7515151515151515,0.03374402644139407,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8434343434343434,0.025890520358141458,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8704663212435233,0.024233532297758688,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.6974358974358974,0.02329088805377271,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45185185185185184,0.030343862998512657,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7563025210084033,0.027886828078380516,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_physics,5,lm-eval,vllm,,acc,none,0.5298013245033113,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8403669724770643,0.015703498348461794,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6805555555555556,0.03179876342176851,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.7941176470588235,0.028379449451588684,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8312236286919831,0.02438140683258622,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_human_aging,5,lm-eval,vllm,,acc,none,0.6860986547085202,0.031146796482972486,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7709923664122137,0.036853466317118506,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_humanities,5,lm-eval,vllm,yes,acc,none,0.5664187035069076,0.006700052229425896,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_international_law,5,lm-eval,vllm,,acc,none,0.8347107438016529,0.03390780612972774,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_jurisprudence,5,lm-eval,vllm,,acc,none,0.7592592592592593,0.041331194402438355,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6625766871165644,0.03714908409935573,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_machine_learning,5,lm-eval,vllm,,acc,none,0.5357142857142857,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_management,5,lm-eval,vllm,,acc,none,0.8058252427184466,0.03916667762822582,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_marketing,5,lm-eval,vllm,,acc,none,0.8376068376068376,0.024161618127987734,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7318007662835249,0.01584243083526941,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_moral_disputes,5,lm-eval,vllm,,acc,none,0.6965317919075145,0.024752411960917278,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.28268156424581004,0.015060381730018045,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_nutrition,5,lm-eval,vllm,,acc,none,0.696078431372549,0.026336613469046647,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_other,5,lm-eval,vllm,yes,acc,none,0.6681686514322498,0.008224294481352985,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_philosophy,5,lm-eval,vllm,,acc,none,0.7170418006430869,0.025583062489984907,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_prehistory,5,lm-eval,vllm,,acc,none,0.7438271604938271,0.02428853363772609,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_professional_accounting,5,lm-eval,vllm,,acc,none,0.4397163120567376,0.029609912075594054,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_professional_law,5,lm-eval,vllm,,acc,none,0.47196870925684486,0.012750151802922528,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6801470588235294,0.028332959514031246,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_professional_psychology,5,lm-eval,vllm,,acc,none,0.6650326797385621,0.01909422816700032,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_security_studies,5,lm-eval,vllm,,acc,none,0.7959183673469388,0.02580128347509046,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7559311017224569,0.007585457531426443,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_sociology,5,lm-eval,vllm,,acc,none,0.8109452736318408,0.02768691358801299,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_stem,5,lm-eval,vllm,yes,acc,none,0.6343165239454488,0.008322325851532676,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_virology,5,lm-eval,vllm,,acc,none,0.5301204819277109,0.03885425420866771,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_lt_world_religions,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.03126781714663182,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7a28f45237_2026-10-07T15-41-25.038615.json,1791387352.0155935,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl,5,lm-eval,vllm,yes,acc,none,0.6805298390542658,0.003776973975323213,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_anatomy,5,lm-eval,vllm,,acc,none,0.6074074074074074,0.04218506215368885,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_astronomy,5,lm-eval,vllm,,acc,none,0.8026315789473685,0.032389816016993984,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_business_ethics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7018867924528301,0.028152837942493784,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_college_biology,5,lm-eval,vllm,,acc,none,0.8263888888888888,0.03167473383795719,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_college_medicine,5,lm-eval,vllm,,acc,none,0.6878612716763006,0.03533133389323657,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_college_physics,5,lm-eval,vllm,,acc,none,0.5196078431372549,0.049713588843674016,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7361702127659574,0.028809989854102946,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_econometrics,5,lm-eval,vllm,,acc,none,0.5614035087719298,0.04668000738510451,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6758620689655173,0.03900432069185552,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6375661375661376,0.024757473902752066,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_formal_logic,5,lm-eval,vllm,,acc,none,0.5873015873015873,0.04403438954768178,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_global_facts,5,lm-eval,vllm,,acc,none,0.4,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8387096774193549,0.020923327006423326,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6305418719211823,0.03395970381998578,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.793939393939394,0.03158415324047706,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026552207828215258,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.917098445595855,0.019899341315721786,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7564102564102564,0.021763733684173926,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.4962962962962963,0.030484701665084435,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8109243697478992,0.025435119438105305,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_physics,5,lm-eval,vllm,,acc,none,0.5298013245033113,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8697247706422019,0.01443186285247314,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.031919234456861886,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.024857478080250486,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_human_aging,5,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_human_sexuality,5,lm-eval,vllm,,acc,none,0.8244274809160306,0.03336820338476075,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_humanities,5,lm-eval,vllm,yes,acc,none,0.6282678002125398,0.006734472643567773,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_international_law,5,lm-eval,vllm,,acc,none,0.8264462809917356,0.03457272836917668,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7870370370370371,0.03957835471980979,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7423312883435583,0.03436150827846915,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_machine_learning,5,lm-eval,vllm,,acc,none,0.625,0.04595091388086298,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_marketing,5,lm-eval,vllm,,acc,none,0.8589743589743589,0.022801382534597486,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_medical_genetics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7624521072796935,0.015218733046150228,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7196531791907514,0.024182427496577626,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.48156424581005586,0.016711130497782726,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_nutrition,5,lm-eval,vllm,,acc,none,0.7189542483660131,0.025738854797818695,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_other,5,lm-eval,vllm,yes,acc,none,0.6871580302542646,0.008068535394072646,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_philosophy,5,lm-eval,vllm,,acc,none,0.7427652733118971,0.0248261712892509,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_prehistory,5,lm-eval,vllm,,acc,none,0.7839506172839507,0.02289916291844576,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_professional_accounting,5,lm-eval,vllm,,acc,none,0.4574468085106383,0.029719281272236827,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_professional_law,5,lm-eval,vllm,,acc,none,0.5032594524119948,0.012769964760343448,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6433823529411765,0.029097209568412025,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_professional_psychology,5,lm-eval,vllm,,acc,none,0.6879084967320261,0.018745011201277615,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_security_studies,5,lm-eval,vllm,,acc,none,0.763265306122449,0.027212835884073104,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7825804354891128,0.0072898128630718316,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_sociology,5,lm-eval,vllm,,acc,none,0.8258706467661692,0.026814951200421624,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_stem,5,lm-eval,vllm,yes,acc,none,0.6523945448778941,0.0082540474489765,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_virology,5,lm-eval,vllm,,acc,none,0.5240963855421686,0.03887971849597267,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_nl_world_religions,5,lm-eval,vllm,,acc,none,0.7953216374269005,0.03094445977853322,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4e6f098f91_2026-10-07T16-51-13.725061.json,1791391525.8306031,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl,5,lm-eval,vllm,yes,acc,none,0.6645064805583251,0.003801373651733625,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_abstract_algebra,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_anatomy,5,lm-eval,vllm,,acc,none,0.5333333333333333,0.043097329010363616,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_astronomy,5,lm-eval,vllm,,acc,none,0.7368421052631579,0.03583496176361067,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_business_ethics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6981132075471698,0.028254200344438735,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_college_biology,5,lm-eval,vllm,,acc,none,0.7638888888888888,0.03551446610810825,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_college_computer_science,5,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_computer_security,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7063829787234043,0.02977164271249127,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_electrical_engineering,5,lm-eval,vllm,,acc,none,0.696551724137931,0.03831226048850335,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.024552292209342713,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_formal_logic,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.042639068927951274,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_global_facts,5,lm-eval,vllm,,acc,none,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_biology,5,lm-eval,vllm,,acc,none,0.8193548387096774,0.021886178567172513,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6354679802955665,0.033864057460620954,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8121212121212121,0.030501934059429147,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_geography,5,lm-eval,vllm,,acc,none,0.8131313131313131,0.02777253333421894,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8756476683937824,0.02381447708659357,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7564102564102564,0.021763733684173926,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.46296296296296297,0.03040178640610153,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7857142857142857,0.026653531596715505,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_physics,5,lm-eval,vllm,,acc,none,0.4900662251655629,0.040816771072484305,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8532110091743119,0.015173141845126333,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6620370370370371,0.03225941352631297,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8578431372549019,0.024509803921568627,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8481012658227848,0.023363878096632425,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_human_aging,5,lm-eval,vllm,,acc,none,0.6905829596412556,0.031024411740572237,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_humanities,5,lm-eval,vllm,yes,acc,none,0.6034006376195536,0.006722817862260482,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_international_law,5,lm-eval,vllm,,acc,none,0.8099173553719008,0.03581796951709283,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_jurisprudence,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.0437331304091476,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7116564417177914,0.03559039531617345,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_machine_learning,5,lm-eval,vllm,,acc,none,0.5,0.04745789978762494,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_marketing,5,lm-eval,vllm,,acc,none,0.8675213675213675,0.022209309073165668,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_medical_genetics,5,lm-eval,vllm,,acc,none,0.64,0.048241815132442176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_miscellaneous,5,lm-eval,vllm,,acc,none,0.7535121328224776,0.015411308769686863,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_moral_disputes,5,lm-eval,vllm,,acc,none,0.7369942196531792,0.023703099525258117,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4011173184357542,0.01639222189940706,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_nutrition,5,lm-eval,vllm,,acc,none,0.7287581699346405,0.025457756696667815,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_other,5,lm-eval,vllm,yes,acc,none,0.6813646604441583,0.008090743819279444,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_philosophy,5,lm-eval,vllm,,acc,none,0.707395498392283,0.02583989833487794,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_prehistory,5,lm-eval,vllm,,acc,none,0.7407407407407407,0.024383665531035527,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_professional_accounting,5,lm-eval,vllm,,acc,none,0.41843971631205673,0.02942799403941995,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_professional_law,5,lm-eval,vllm,,acc,none,0.4810951760104302,0.012761104871472521,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_professional_medicine,5,lm-eval,vllm,,acc,none,0.6838235294117647,0.028245687391462857,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_professional_psychology,5,lm-eval,vllm,,acc,none,0.684640522875817,0.01879808628488684,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_public_relations,5,lm-eval,vllm,,acc,none,0.6818181818181818,0.044612721759105065,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_security_studies,5,lm-eval,vllm,,acc,none,0.8122448979591836,0.025000256039546167,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7712057198570036,0.0074325091745685535,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_stem,5,lm-eval,vllm,yes,acc,none,0.6349508404693942,0.008354655542233707,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pl_world_religions,5,lm-eval,vllm,,acc,none,0.8421052631578947,0.027966785859160903,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d6a90e5482_2026-10-07T16-24-30.196687.json,1791389927.7548995,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt,5,lm-eval,vllm,yes,acc,none,0.6848027346531833,0.003741019392959301,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_abstract_algebra,5,lm-eval,vllm,,acc,none,0.39,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_anatomy,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.0417165416135454,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7433962264150943,0.02688064788905203,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_college_biology,5,lm-eval,vllm,,acc,none,0.8055555555555556,0.03309615177059002,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_college_chemistry,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_college_computer_science,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_college_mathematics,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_computer_security,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7404255319148936,0.02865917937429237,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_econometrics,5,lm-eval,vllm,,acc,none,0.5789473684210527,0.04644602091222323,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_electrical_engineering,5,lm-eval,vllm,,acc,none,0.696551724137931,0.03831226048850335,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6164021164021164,0.0250437573185202,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_formal_logic,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.042639068927951274,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_global_facts,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6551724137931034,0.03344283744280457,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_european_history,5,lm-eval,vllm,,acc,none,0.806060606060606,0.030874145136562132,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_geography,5,lm-eval,vllm,,acc,none,0.8484848484848485,0.025545650426603637,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9119170984455959,0.020453746601601056,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7282051282051282,0.02255655101013233,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7941176470588235,0.026265024608275907,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_physics,5,lm-eval,vllm,,acc,none,0.5629139072847682,0.040500357222306375,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8733944954128441,0.014257128686165186,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6574074074074074,0.0323658525260216,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8431372549019608,0.02552472232455332,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_human_aging,5,lm-eval,vllm,,acc,none,0.7354260089686099,0.029605103217038367,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_human_sexuality,5,lm-eval,vllm,,acc,none,0.7938931297709924,0.035477710041594654,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_humanities,5,lm-eval,vllm,yes,acc,none,0.6208289054197662,0.006692629539030597,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_jurisprudence,5,lm-eval,vllm,,acc,none,0.7962962962962963,0.038935425188248496,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7423312883435583,0.03436150827846915,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_machine_learning,5,lm-eval,vllm,,acc,none,0.5625,0.04708567521880525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_management,5,lm-eval,vllm,,acc,none,0.8155339805825242,0.038404236272882766,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_marketing,5,lm-eval,vllm,,acc,none,0.8290598290598291,0.024662496845209797,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_medical_genetics,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_miscellaneous,5,lm-eval,vllm,,acc,none,0.7841634738186463,0.01471168438613984,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_moral_disputes,5,lm-eval,vllm,,acc,none,0.7630057803468208,0.02289408248992599,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4223463687150838,0.016519594275297204,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_nutrition,5,lm-eval,vllm,,acc,none,0.7549019607843137,0.024630048979824716,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_other,5,lm-eval,vllm,yes,acc,none,0.7090440939813325,0.007912162484964482,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_philosophy,5,lm-eval,vllm,,acc,none,0.7202572347266881,0.02549425935069486,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_prehistory,5,lm-eval,vllm,,acc,none,0.7716049382716049,0.02335821184062624,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_professional_accounting,5,lm-eval,vllm,,acc,none,0.4716312056737589,0.029779450957303062,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_professional_law,5,lm-eval,vllm,,acc,none,0.5032594524119948,0.012769964760343448,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_professional_medicine,5,lm-eval,vllm,,acc,none,0.6948529411764706,0.02797154137017067,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_professional_psychology,5,lm-eval,vllm,,acc,none,0.7320261437908496,0.01791797406959478,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_public_relations,5,lm-eval,vllm,,acc,none,0.6909090909090909,0.04426294648200096,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_security_studies,5,lm-eval,vllm,,acc,none,0.7959183673469388,0.02580128347509046,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7907052323691908,0.0072182552451673185,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_sociology,5,lm-eval,vllm,,acc,none,0.8159203980099502,0.027403859410786886,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_stem,5,lm-eval,vllm,yes,acc,none,0.6530288614018395,0.00821185111351739,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_virology,5,lm-eval,vllm,,acc,none,0.5421686746987951,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_pt_world_religions,5,lm-eval,vllm,,acc,none,0.8070175438596491,0.030267457554898448,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/060a6a39bd_2026-10-07T16-08-06.355595.json,1791388945.380746,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro,5,lm-eval,vllm,yes,acc,none,0.6802449793476713,0.0037592374204038718,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_abstract_algebra,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_anatomy,5,lm-eval,vllm,,acc,none,0.6,0.0423207369515159,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_astronomy,5,lm-eval,vllm,,acc,none,0.7763157894736842,0.033911609343436046,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_business_ethics,5,lm-eval,vllm,,acc,none,0.65,0.04793724854411023,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.720754716981132,0.027611163402399694,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_college_biology,5,lm-eval,vllm,,acc,none,0.7708333333333334,0.03514697467862389,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_college_chemistry,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_college_mathematics,5,lm-eval,vllm,,acc,none,0.51,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_college_medicine,5,lm-eval,vllm,,acc,none,0.7225433526011561,0.03414014007044037,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_college_physics,5,lm-eval,vllm,,acc,none,0.5098039215686274,0.04974229460422813,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_computer_security,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7319148936170212,0.028957342788342354,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_econometrics,5,lm-eval,vllm,,acc,none,0.5175438596491229,0.04700708033551044,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7310344827586207,0.03695183311650232,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6375661375661376,0.024757473902752066,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_formal_logic,5,lm-eval,vllm,,acc,none,0.6111111111111112,0.043603148600774626,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_global_facts,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.625615763546798,0.03405155380561957,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.030117688929503603,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_geography,5,lm-eval,vllm,,acc,none,0.8333333333333334,0.026552207828215258,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9015544041450777,0.021500249576033463,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7743589743589744,0.021193632525148505,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48518518518518516,0.030472153249328608,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8361344537815126,0.024044054940440488,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_physics,5,lm-eval,vllm,,acc,none,0.543046357615894,0.0406732517424744,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8495412844036697,0.015328563932669235,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6712962962962963,0.03203614084670054,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8088235294117647,0.02759917430064072,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8481012658227848,0.023363878096632425,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_human_aging,5,lm-eval,vllm,,acc,none,0.7309417040358744,0.029763779406874906,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_human_sexuality,5,lm-eval,vllm,,acc,none,0.8015267175572519,0.034981493854624734,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_humanities,5,lm-eval,vllm,yes,acc,none,0.6180658873538789,0.0066934191474782865,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_international_law,5,lm-eval,vllm,,acc,none,0.8512396694214877,0.03248470083807198,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_jurisprudence,5,lm-eval,vllm,,acc,none,0.7407407407407407,0.04236511258094632,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_logical_fallacies,5,lm-eval,vllm,,acc,none,0.754601226993865,0.033809398139433525,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_machine_learning,5,lm-eval,vllm,,acc,none,0.5,0.04745789978762494,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_management,5,lm-eval,vllm,,acc,none,0.7961165048543689,0.0398913985953177,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_marketing,5,lm-eval,vllm,,acc,none,0.9017094017094017,0.019503444900757564,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_medical_genetics,5,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_miscellaneous,5,lm-eval,vllm,,acc,none,0.7726692209450831,0.014987270640946054,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_moral_disputes,5,lm-eval,vllm,,acc,none,0.7658959537572254,0.022797110278071155,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4111731843575419,0.016456498033977494,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_nutrition,5,lm-eval,vllm,,acc,none,0.7254901960784313,0.0255531699918265,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_other,5,lm-eval,vllm,yes,acc,none,0.7013196009011908,0.00796241313033831,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_philosophy,5,lm-eval,vllm,,acc,none,0.7331189710610932,0.0251226376088166,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_prehistory,5,lm-eval,vllm,,acc,none,0.7746913580246914,0.02324620264781973,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_professional_accounting,5,lm-eval,vllm,,acc,none,0.48226950354609927,0.02980873964223769,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_professional_law,5,lm-eval,vllm,,acc,none,0.5045632333767927,0.012769704263117505,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_professional_medicine,5,lm-eval,vllm,,acc,none,0.6617647058823529,0.028739328513983604,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_professional_psychology,5,lm-eval,vllm,,acc,none,0.7058823529411765,0.01843342764940195,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_public_relations,5,lm-eval,vllm,,acc,none,0.7090909090909091,0.04350271442923247,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_security_studies,5,lm-eval,vllm,,acc,none,0.7591836734693878,0.027372942201788125,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7842053948651284,0.007290248196091425,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_sociology,5,lm-eval,vllm,,acc,none,0.8258706467661692,0.026814951200421624,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_stem,5,lm-eval,vllm,yes,acc,none,0.6508087535680305,0.008267613532640002,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_virology,5,lm-eval,vllm,,acc,none,0.5120481927710844,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_ro_world_religions,5,lm-eval,vllm,,acc,none,0.8070175438596491,0.030267457554898448,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/661a02608f_2026-10-07T16-47-05.760298.json,1791391280.512971,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr,5,lm-eval,vllm,yes,acc,none,0.6444238712434126,0.0038815965978653963,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.42,0.04960449637488583,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_anatomy,5,lm-eval,vllm,,acc,none,0.562962962962963,0.042849586397534056,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_astronomy,5,lm-eval,vllm,,acc,none,0.7631578947368421,0.03459777606810534,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_business_ethics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6716981132075471,0.028901593612411777,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_college_biology,5,lm-eval,vllm,,acc,none,0.7430555555555556,0.03653946969442102,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_college_chemistry,5,lm-eval,vllm,,acc,none,0.47,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_college_computer_science,5,lm-eval,vllm,,acc,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_college_medicine,5,lm-eval,vllm,,acc,none,0.6589595375722543,0.03614665424180821,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_college_physics,5,lm-eval,vllm,,acc,none,0.4803921568627451,0.04971358884367401,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_computer_security,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7021276595744681,0.029896145682095487,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_econometrics,5,lm-eval,vllm,,acc,none,0.47368421052631576,0.046970851366478654,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6344827586206897,0.04013124195424389,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6534391534391535,0.024508777521028414,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_global_facts,5,lm-eval,vllm,,acc,none,0.38,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_biology,5,lm-eval,vllm,,acc,none,0.8193548387096774,0.021886178567172513,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5665024630541872,0.034867317274198714,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7818181818181819,0.032250781083062896,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7929292929292929,0.02886977846026699,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8601036269430051,0.025033870583015143,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7,0.02323458108842843,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.46296296296296297,0.03040178640610153,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7605042016806722,0.02772206549336123,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8256880733944955,0.01626567563201035,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6435185185185185,0.03266478331527272,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.803921568627451,0.027865942286639318,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.869198312236287,0.02194876605947081,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_human_aging,5,lm-eval,vllm,,acc,none,0.6547085201793722,0.03191100192835789,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7404580152671756,0.03844876139785267,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_humanities,5,lm-eval,vllm,yes,acc,none,0.5889479277364505,0.006830183711843155,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_international_law,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.03520893951097652,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_jurisprudence,5,lm-eval,vllm,,acc,none,0.6759259259259259,0.04524596007030053,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.656441717791411,0.037311335196738946,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_machine_learning,5,lm-eval,vllm,,acc,none,0.5446428571428571,0.04726835553719097,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_marketing,5,lm-eval,vllm,,acc,none,0.8461538461538461,0.023636873317489267,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_medical_genetics,5,lm-eval,vllm,,acc,none,0.61,0.04902071300001973,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_miscellaneous,5,lm-eval,vllm,,acc,none,0.6909323116219668,0.016524988919702232,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_moral_disputes,5,lm-eval,vllm,,acc,none,0.7254335260115607,0.02402774515526503,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4324022346368715,0.016568971233548446,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_nutrition,5,lm-eval,vllm,,acc,none,0.7156862745098039,0.025829163272757385,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_other,5,lm-eval,vllm,yes,acc,none,0.6504666881235919,0.008337327447109818,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_philosophy,5,lm-eval,vllm,,acc,none,0.7106109324758842,0.02575586592263286,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_prehistory,5,lm-eval,vllm,,acc,none,0.6975308641975309,0.025557653981868003,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_professional_accounting,5,lm-eval,vllm,,acc,none,0.4326241134751773,0.029555454236778834,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_professional_law,5,lm-eval,vllm,,acc,none,0.46088657105606257,0.012731102790504536,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6360294117647058,0.029227192460031966,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6683006535947712,0.019047485239360454,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_public_relations,5,lm-eval,vllm,,acc,none,0.6454545454545455,0.04582004841505413,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_security_studies,5,lm-eval,vllm,,acc,none,0.7551020408163265,0.02752963744017492,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7435814104647384,0.007737625798350767,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_sociology,5,lm-eval,vllm,,acc,none,0.8009950248756219,0.02823136509275842,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_stem,5,lm-eval,vllm,yes,acc,none,0.6244846178242943,0.008392843027356968,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sr_world_religions,5,lm-eval,vllm,,acc,none,0.7602339181286549,0.03274485211946959,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9ec0bd3b50_2026-10-07T16-16-35.354216.json,1791389444.1658847,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv,5,lm-eval,vllm,yes,acc,none,0.6799601196410767,0.003756514147930905,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_abstract_algebra,5,lm-eval,vllm,,acc,none,0.41,0.04943110704237104,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_anatomy,5,lm-eval,vllm,,acc,none,0.6222222222222222,0.041883075375958506,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_astronomy,5,lm-eval,vllm,,acc,none,0.8223684210526315,0.03110318238312337,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_business_ethics,5,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7358490566037735,0.02713429162874164,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_college_biology,5,lm-eval,vllm,,acc,none,0.7916666666666666,0.03396116205845331,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_college_computer_science,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_college_mathematics,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_college_medicine,5,lm-eval,vllm,,acc,none,0.6820809248554913,0.0355068398916558,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7191489361702128,0.029379170464124797,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_econometrics,5,lm-eval,vllm,,acc,none,0.5701754385964912,0.04657047260594963,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_electrical_engineering,5,lm-eval,vllm,,acc,none,0.696551724137931,0.03831226048850335,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6613756613756614,0.024373197867983004,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_formal_logic,5,lm-eval,vllm,,acc,none,0.6428571428571429,0.04285714285714286,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_global_facts,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_biology,5,lm-eval,vllm,,acc,none,0.8419354838709677,0.020752831511875243,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6206896551724138,0.034139638059062394,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8,0.031234752377721213,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_geography,5,lm-eval,vllm,,acc,none,0.8787878787878788,0.02325315795194205,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8756476683937824,0.02381447708659357,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7615384615384615,0.021606294494647772,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.48148148148148145,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8025210084033614,0.0258591641220515,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_physics,5,lm-eval,vllm,,acc,none,0.5165562913907285,0.0408024418562897,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8752293577981651,0.014168298359156423,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6574074074074074,0.0323658525260216,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8529411764705882,0.024857478080250486,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8354430379746836,0.024135736240566936,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_human_aging,5,lm-eval,vllm,,acc,none,0.7399103139013453,0.029442495585857424,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_human_sexuality,5,lm-eval,vllm,,acc,none,0.8091603053435115,0.03446513350752599,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_humanities,5,lm-eval,vllm,yes,acc,none,0.6233793836344315,0.006724044762789908,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_international_law,5,lm-eval,vllm,,acc,none,0.8181818181818182,0.03520893951097652,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_jurisprudence,5,lm-eval,vllm,,acc,none,0.7314814814814815,0.04284467968052193,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6932515337423313,0.036230899157241474,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_machine_learning,5,lm-eval,vllm,,acc,none,0.4732142857142857,0.047389751192741525,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_management,5,lm-eval,vllm,,acc,none,0.7864077669902912,0.04058042015646035,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_marketing,5,lm-eval,vllm,,acc,none,0.9017094017094017,0.019503444900757564,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_medical_genetics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_miscellaneous,5,lm-eval,vllm,,acc,none,0.7662835249042146,0.015133383278988898,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_moral_disputes,5,lm-eval,vllm,,acc,none,0.7456647398843931,0.02344582627654551,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_moral_scenarios,5,lm-eval,vllm,,acc,none,0.4592178770949721,0.016666783616525672,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_nutrition,5,lm-eval,vllm,,acc,none,0.7483660130718954,0.024848018263875137,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_other,5,lm-eval,vllm,yes,acc,none,0.6948825233344061,0.007954547321883923,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_philosophy,5,lm-eval,vllm,,acc,none,0.7234726688102894,0.025403832978179643,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_prehistory,5,lm-eval,vllm,,acc,none,0.7901234567901234,0.022658344085981406,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_professional_accounting,5,lm-eval,vllm,,acc,none,0.4397163120567376,0.029609912075594054,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_professional_law,5,lm-eval,vllm,,acc,none,0.4980443285528031,0.012770138422208597,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_professional_medicine,5,lm-eval,vllm,,acc,none,0.6617647058823529,0.028739328513983604,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_professional_psychology,5,lm-eval,vllm,,acc,none,0.704248366013072,0.01846315413263271,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_security_studies,5,lm-eval,vllm,,acc,none,0.7714285714285715,0.026882144922307713,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7877803054923627,0.00724148509025254,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_sociology,5,lm-eval,vllm,,acc,none,0.8308457711442786,0.026508590656233278,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_stem,5,lm-eval,vllm,yes,acc,none,0.6444655883285759,0.008235700909042715,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_virology,5,lm-eval,vllm,,acc,none,0.4939759036144578,0.03892212195333041,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_sv_world_religions,5,lm-eval,vllm,,acc,none,0.8362573099415205,0.02838091959614585,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/112e788e59_2026-10-07T16-34-37.323683.json,1791390544.0653694,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr,5,lm-eval,vllm,yes,acc,none,0.6358068651189289,0.0038695012769740474,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_abstract_algebra,5,lm-eval,vllm,,acc,none,0.34,0.04760952285695233,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_anatomy,5,lm-eval,vllm,,acc,none,0.6,0.0423207369515159,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_astronomy,5,lm-eval,vllm,,acc,none,0.7763157894736842,0.033911609343436046,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_business_ethics,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_college_biology,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.037455547914624555,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_college_chemistry,5,lm-eval,vllm,,acc,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_college_computer_science,5,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_college_mathematics,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_college_medicine,5,lm-eval,vllm,,acc,none,0.6473988439306358,0.03643037168958545,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_college_physics,5,lm-eval,vllm,,acc,none,0.4411764705882353,0.049406356306056644,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_computer_security,5,lm-eval,vllm,,acc,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_conceptual_physics,5,lm-eval,vllm,,acc,none,0.6808510638297872,0.03047297336338012,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_econometrics,5,lm-eval,vllm,,acc,none,0.49122807017543857,0.0470288043204961,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6413793103448275,0.03996629574876715,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6243386243386243,0.02494236893115981,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_formal_logic,5,lm-eval,vllm,,acc,none,0.6190476190476191,0.043435254289490965,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_global_facts,5,lm-eval,vllm,,acc,none,0.34,0.04760952285695233,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_biology,5,lm-eval,vllm,,acc,none,0.7870967741935484,0.023287665127268594,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6108374384236454,0.03430462416103873,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_european_history,5,lm-eval,vllm,,acc,none,0.7151515151515152,0.03524390844511785,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_geography,5,lm-eval,vllm,,acc,none,0.7878787878787878,0.029126522834586777,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.7772020725388601,0.030031147977641528,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7025641025641025,0.02317740813146596,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.45925925925925926,0.030384169232350797,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7521008403361344,0.028047967224176896,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_physics,5,lm-eval,vllm,,acc,none,0.47019867549668876,0.0407522499221698,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8440366972477065,0.015555802713590066,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6296296296296297,0.03293377139415187,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8284313725490197,0.026460569561240675,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8185654008438819,0.025085961144579647,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_human_aging,5,lm-eval,vllm,,acc,none,0.6591928251121076,0.03181149747055356,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_human_sexuality,5,lm-eval,vllm,,acc,none,0.7709923664122137,0.036853466317118506,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_humanities,5,lm-eval,vllm,yes,acc,none,0.5676939426142402,0.006748855268947085,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_jurisprudence,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.0437331304091476,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6932515337423313,0.036230899157241474,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_machine_learning,5,lm-eval,vllm,,acc,none,0.5357142857142857,0.04733667890053756,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_management,5,lm-eval,vllm,,acc,none,0.7475728155339806,0.04301250399690879,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_marketing,5,lm-eval,vllm,,acc,none,0.8547008547008547,0.02308663508684137,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_medical_genetics,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_miscellaneous,5,lm-eval,vllm,,acc,none,0.7305236270753512,0.01586624307321501,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_moral_disputes,5,lm-eval,vllm,,acc,none,0.6965317919075145,0.024752411960917278,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_moral_scenarios,5,lm-eval,vllm,,acc,none,0.3039106145251397,0.015382845587584475,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_nutrition,5,lm-eval,vllm,,acc,none,0.6895424836601307,0.026493033225145922,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_other,5,lm-eval,vllm,yes,acc,none,0.6626971355004828,0.008247371929752069,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_philosophy,5,lm-eval,vllm,,acc,none,0.7138263665594855,0.02567025924218898,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_prehistory,5,lm-eval,vllm,,acc,none,0.7129629629629629,0.025171041915309698,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_professional_accounting,5,lm-eval,vllm,,acc,none,0.46099290780141844,0.029736592526424455,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_professional_law,5,lm-eval,vllm,,acc,none,0.47131681877444587,0.012749206007657478,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_professional_medicine,5,lm-eval,vllm,,acc,none,0.6470588235294118,0.02902942281568144,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_professional_psychology,5,lm-eval,vllm,,acc,none,0.6470588235294118,0.019333142020797084,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_public_relations,5,lm-eval,vllm,,acc,none,0.6545454545454545,0.045546196175410524,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_security_studies,5,lm-eval,vllm,,acc,none,0.746938775510204,0.027833023871399704,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7361065973350667,0.007818123910663383,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_sociology,5,lm-eval,vllm,,acc,none,0.7810945273631841,0.02923917463664699,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_stem,5,lm-eval,vllm,yes,acc,none,0.6130669203932763,0.008443938931514038,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_tr_world_religions,5,lm-eval,vllm,,acc,none,0.7660818713450293,0.032467217651178305,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/76b3db0ec7_2026-10-07T16-12-15.630098.json,1791389189.1543446,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk,5,lm-eval,vllm,yes,acc,none,0.6472724683093577,0.003845070252432011,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_abstract_algebra,5,lm-eval,vllm,,acc,none,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_anatomy,5,lm-eval,vllm,,acc,none,0.5703703703703704,0.04276349494376599,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_astronomy,5,lm-eval,vllm,,acc,none,0.7894736842105263,0.033176727875331595,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_business_ethics,5,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.6867924528301886,0.02854479331905527,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_college_biology,5,lm-eval,vllm,,acc,none,0.7291666666666666,0.03716177437566019,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_college_computer_science,5,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_college_mathematics,5,lm-eval,vllm,,acc,none,0.49,0.05024183937956913,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_college_medicine,5,lm-eval,vllm,,acc,none,0.6705202312138728,0.03583901754736415,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_college_physics,5,lm-eval,vllm,,acc,none,0.46078431372549017,0.049598599663841836,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_computer_security,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7191489361702128,0.029379170464124797,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_econometrics,5,lm-eval,vllm,,acc,none,0.4649122807017544,0.04692008381368906,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_electrical_engineering,5,lm-eval,vllm,,acc,none,0.6137931034482759,0.04057324734419032,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.024552292209342713,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_formal_logic,5,lm-eval,vllm,,acc,none,0.5634920634920635,0.044359328928514664,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_global_facts,5,lm-eval,vllm,,acc,none,0.43,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_biology,5,lm-eval,vllm,,acc,none,0.8129032258064516,0.02218571009225229,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.5911330049261084,0.034590588158832314,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_european_history,5,lm-eval,vllm,,acc,none,0.793939393939394,0.03158415324047706,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_geography,5,lm-eval,vllm,,acc,none,0.8282828282828283,0.02686971618742987,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.8963730569948186,0.021995311963644265,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7256410256410256,0.022622765767493235,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.43333333333333335,0.030213340289238,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.7983193277310925,0.026064313406304485,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_physics,5,lm-eval,vllm,,acc,none,0.5033112582781457,0.04082393379449653,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_psychology,5,lm-eval,vllm,,acc,none,0.8348623853211009,0.015919557829976096,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6666666666666666,0.03214952147802747,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8137254901960784,0.027325470966716357,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8185654008438819,0.025085961144579647,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_human_aging,5,lm-eval,vllm,,acc,none,0.7040358744394619,0.03063659134869978,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_human_sexuality,5,lm-eval,vllm,,acc,none,0.7633587786259542,0.03727673575596918,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_humanities,5,lm-eval,vllm,yes,acc,none,0.5774707757704569,0.006786281135912683,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_jurisprudence,5,lm-eval,vllm,,acc,none,0.7222222222222222,0.04330043749650743,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_logical_fallacies,5,lm-eval,vllm,,acc,none,0.6809815950920245,0.03661997551073836,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_machine_learning,5,lm-eval,vllm,,acc,none,0.5714285714285714,0.04697113923010208,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_management,5,lm-eval,vllm,,acc,none,0.7572815533980582,0.04245022486384496,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_marketing,5,lm-eval,vllm,,acc,none,0.8504273504273504,0.023365051491753757,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_medical_genetics,5,lm-eval,vllm,,acc,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_miscellaneous,5,lm-eval,vllm,,acc,none,0.6922094508301405,0.0165060450451556,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_moral_disputes,5,lm-eval,vllm,,acc,none,0.7341040462427746,0.02378620325550823,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_moral_scenarios,5,lm-eval,vllm,,acc,none,0.34301675977653634,0.015876912673057682,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_nutrition,5,lm-eval,vllm,,acc,none,0.738562091503268,0.025160998214292445,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_other,5,lm-eval,vllm,yes,acc,none,0.6633408432571613,0.008262370289390128,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_philosophy,5,lm-eval,vllm,,acc,none,0.6945337620578779,0.026160584450140488,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_prehistory,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.025630824975621306,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_professional_accounting,5,lm-eval,vllm,,acc,none,0.4326241134751773,0.029555454236778834,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_professional_law,5,lm-eval,vllm,,acc,none,0.4791395045632334,0.012759117066518041,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_professional_medicine,5,lm-eval,vllm,,acc,none,0.6617647058823529,0.028739328513983604,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_professional_psychology,5,lm-eval,vllm,,acc,none,0.6486928104575164,0.01931267606578656,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_public_relations,5,lm-eval,vllm,,acc,none,0.6636363636363637,0.04525393596302509,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_security_studies,5,lm-eval,vllm,,acc,none,0.7877551020408163,0.026176967197866795,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_social_sciences,5,lm-eval,vllm,yes,acc,none,0.7559311017224569,0.007565097233355105,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_sociology,5,lm-eval,vllm,,acc,none,0.8059701492537313,0.02796267760476895,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_stem,5,lm-eval,vllm,yes,acc,none,0.6295591500158579,0.008360432156837091,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.83,0.03775251680686369,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_virology,5,lm-eval,vllm,,acc,none,0.4879518072289157,0.038913644958358196,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_mmlu_full_uk_world_religions,5,lm-eval,vllm,,acc,none,0.7426900584795322,0.03352799844161867,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1bfd4c31a9_2026-10-07T16-12-25.625879.json,1791389194.1688356,1 +v2anneal_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f0982d35fa_2026-10-07T16-05-07.115115.json,1791388945.2133884,1 +v2anneal_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_bytes,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f0982d35fa_2026-10-07T16-05-07.115115.json,1791388945.2133884,1 +v2anneal_merge3_116k_120k,global_piqa_completions_als_latn,0,lm-eval,vllm,,acc_norm,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f0982d35fa_2026-10-07T16-05-07.115115.json,1791388945.2133884,1 +v2anneal_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7f84b052ed_2026-10-07T16-21-32.082823.json,1791389928.2022226,1 +v2anneal_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_bytes,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7f84b052ed_2026-10-07T16-21-32.082823.json,1791389928.2022226,1 +v2anneal_merge3_116k_120k,global_piqa_completions_bos_latn,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7f84b052ed_2026-10-07T16-21-32.082823.json,1791389928.2022226,1 +v2anneal_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e2482964aa_2026-10-07T16-27-32.739967.json,1791390292.5680118,1 +v2anneal_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e2482964aa_2026-10-07T16-27-32.739967.json,1791390292.5680118,1 +v2anneal_merge3_116k_120k,global_piqa_completions_bul_cyrl,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e2482964aa_2026-10-07T16-27-32.739967.json,1791390292.5680118,1 +v2anneal_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c7baf6935a_2026-10-07T16-15-31.343421.json,1791389566.713873,1 +v2anneal_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_bytes,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c7baf6935a_2026-10-07T16-15-31.343421.json,1791389566.713873,1 +v2anneal_merge3_116k_120k,global_piqa_completions_cat_latn,0,lm-eval,vllm,,acc_norm,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c7baf6935a_2026-10-07T16-15-31.343421.json,1791389566.713873,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a2d5108586_2026-10-07T16-09-05.451491.json,1791389188.8527324,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_bytes,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a2d5108586_2026-10-07T16-09-05.451491.json,1791389188.8527324,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ces_latn,0,lm-eval,vllm,,acc_norm,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a2d5108586_2026-10-07T16-09-05.451491.json,1791389188.8527324,1 +v2anneal_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9879c2edf7_2026-10-07T16-07-05.020614.json,1791389068.6088638,1 +v2anneal_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9879c2edf7_2026-10-07T16-07-05.020614.json,1791389068.6088638,1 +v2anneal_merge3_116k_120k,global_piqa_completions_deu_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9879c2edf7_2026-10-07T16-07-05.020614.json,1791389068.6088638,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ee284f52a8_2026-10-07T16-15-29.511488.json,1791389565.1197233,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ee284f52a8_2026-10-07T16-15-29.511488.json,1791389565.1197233,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ekk_latn,0,lm-eval,vllm,,acc_norm,none,0.67,0.04725815626252609,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ee284f52a8_2026-10-07T16-15-29.511488.json,1791389565.1197233,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d0e1e61317_2026-10-07T16-07-16.527336.json,1791389075.45571,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_bytes,none,0.62,0.04878317312145634,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d0e1e61317_2026-10-07T16-07-16.527336.json,1791389075.45571,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ell_grek,0,lm-eval,vllm,,acc_norm,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d0e1e61317_2026-10-07T16-07-16.527336.json,1791389075.45571,1 +v2anneal_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e48bf47a70_2026-10-07T16-07-31.164562.json,1791389084.8720233,1 +v2anneal_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e48bf47a70_2026-10-07T16-07-31.164562.json,1791389084.8720233,1 +v2anneal_merge3_116k_120k,global_piqa_completions_eng_latn,0,lm-eval,vllm,,acc_norm,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e48bf47a70_2026-10-07T16-07-31.164562.json,1791389084.8720233,1 +v2anneal_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fb6e24923d_2026-10-07T15-38-29.766141.json,1791387352.9426816,1 +v2anneal_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_bytes,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fb6e24923d_2026-10-07T15-38-29.766141.json,1791387352.9426816,1 +v2anneal_merge3_116k_120k,global_piqa_completions_fin_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fb6e24923d_2026-10-07T15-38-29.766141.json,1791387352.9426816,1 +v2anneal_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/46784692fb_2026-10-07T16-29-33.310991.json,1791390416.4491613,1 +v2anneal_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/46784692fb_2026-10-07T16-29-33.310991.json,1791390416.4491613,1 +v2anneal_merge3_116k_120k,global_piqa_completions_fra_latn_fran,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/46784692fb_2026-10-07T16-29-33.310991.json,1791390416.4491613,1 +v2anneal_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d366f66424_2026-10-07T16-13-17.872211.json,1791389438.0364327,1 +v2anneal_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d366f66424_2026-10-07T16-13-17.872211.json,1791389438.0364327,1 +v2anneal_merge3_116k_120k,global_piqa_completions_glg_latn,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d366f66424_2026-10-07T16-13-17.872211.json,1791389438.0364327,1 +v2anneal_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d04c4a8976_2026-10-07T16-23-34.097787.json,1791390050.280016,1 +v2anneal_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_bytes,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d04c4a8976_2026-10-07T16-23-34.097787.json,1791390050.280016,1 +v2anneal_merge3_116k_120k,global_piqa_completions_hrv_latn,0,lm-eval,vllm,,acc_norm,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d04c4a8976_2026-10-07T16-23-34.097787.json,1791390050.280016,1 +v2anneal_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc,none,0.63,0.048523658709390974,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/eaeb8d5e9d_2026-10-07T16-33-44.949083.json,1791390658.758899,1 +v2anneal_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_bytes,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/eaeb8d5e9d_2026-10-07T16-33-44.949083.json,1791390658.758899,1 +v2anneal_merge3_116k_120k,global_piqa_completions_hun_latn,0,lm-eval,vllm,,acc_norm,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/eaeb8d5e9d_2026-10-07T16-33-44.949083.json,1791390658.758899,1 +v2anneal_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc,none,0.66,0.04760952285695234,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/132bf07dbe_2026-10-07T16-13-24.010440.json,1791389444.5511363,1 +v2anneal_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_bytes,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/132bf07dbe_2026-10-07T16-13-24.010440.json,1791389444.5511363,1 +v2anneal_merge3_116k_120k,global_piqa_completions_isl_latn,0,lm-eval,vllm,,acc_norm,none,0.57,0.049756985195624305,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/132bf07dbe_2026-10-07T16-13-24.010440.json,1791389444.5511363,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a804679e2e_2026-10-07T16-27-49.544222.json,1791390303.2095253,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_bytes,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a804679e2e_2026-10-07T16-27-49.544222.json,1791390303.2095253,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ita_latn,0,lm-eval,vllm,,acc_norm,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a804679e2e_2026-10-07T16-27-49.544222.json,1791390303.2095253,1 +v2anneal_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc,none,0.58,0.04960449637488582,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7c718af421_2026-10-07T16-07-13.960874.json,1791389072.2536573,1 +v2anneal_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_bytes,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7c718af421_2026-10-07T16-07-13.960874.json,1791389072.2536573,1 +v2anneal_merge3_116k_120k,global_piqa_completions_kat_geor,0,lm-eval,vllm,,acc_norm,none,0.52,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7c718af421_2026-10-07T16-07-13.960874.json,1791389072.2536573,1 +v2anneal_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc,none,0.7,0.04605661864718383,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7d6d63f966_2026-10-07T16-31-39.416761.json,1791390537.0365617,1 +v2anneal_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7d6d63f966_2026-10-07T16-31-39.416761.json,1791390537.0365617,1 +v2anneal_merge3_116k_120k,global_piqa_completions_lit_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7d6d63f966_2026-10-07T16-31-39.416761.json,1791390537.0365617,1 +v2anneal_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a3948efef6_2026-10-07T16-39-46.413729.json,1791391028.2902973,1 +v2anneal_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a3948efef6_2026-10-07T16-39-46.413729.json,1791391028.2902973,1 +v2anneal_merge3_116k_120k,global_piqa_completions_mkd_cyrl,0,lm-eval,vllm,,acc_norm,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a3948efef6_2026-10-07T16-39-46.413729.json,1791391028.2902973,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc,none,0.77,0.042295258468165065,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/014365cf1b_2026-10-07T16-27-29.623087.json,1791390289.5470872,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_bytes,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/014365cf1b_2026-10-07T16-27-29.623087.json,1791390289.5470872,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nld_latn,0,lm-eval,vllm,,acc_norm,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/014365cf1b_2026-10-07T16-27-29.623087.json,1791390289.5470872,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5272dd9013_2026-10-07T16-46-06.509894.json,1791391404.818416,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_bytes,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5272dd9013_2026-10-07T16-46-06.509894.json,1791391404.818416,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nno_latn,0,lm-eval,vllm,,acc_norm,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5272dd9013_2026-10-07T16-46-06.509894.json,1791391404.818416,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/00a26081b5_2026-10-07T16-07-08.948884.json,1791389072.807083,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_bytes,none,0.72,0.045126085985421296,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/00a26081b5_2026-10-07T16-07-08.948884.json,1791389072.807083,1 +v2anneal_merge3_116k_120k,global_piqa_completions_nob_latn,0,lm-eval,vllm,,acc_norm,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/00a26081b5_2026-10-07T16-07-08.948884.json,1791389072.807083,1 +v2anneal_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ad7b9b650d_2026-10-07T16-05-09.481793.json,1791388951.6497958,1 +v2anneal_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_bytes,none,0.79,0.040936018074033236,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ad7b9b650d_2026-10-07T16-05-09.481793.json,1791388951.6497958,1 +v2anneal_merge3_116k_120k,global_piqa_completions_pol_latn,0,lm-eval,vllm,,acc_norm,none,0.78,0.041633319989322654,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ad7b9b650d_2026-10-07T16-05-09.481793.json,1791388951.6497958,1 +v2anneal_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/05f7142041_2026-10-07T16-07-27.736565.json,1791389084.833074,1 +v2anneal_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_bytes,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/05f7142041_2026-10-07T16-07-27.736565.json,1791389084.833074,1 +v2anneal_merge3_116k_120k,global_piqa_completions_por_latn_port,0,lm-eval,vllm,,acc_norm,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/05f7142041_2026-10-07T16-07-27.736565.json,1791389084.833074,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3717cff2f1_2026-10-07T16-44-01.920503.json,1791391279.1805806,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_bytes,none,0.82,0.03861229196653691,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3717cff2f1_2026-10-07T16-44-01.920503.json,1791391279.1805806,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ron_latn,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3717cff2f1_2026-10-07T16-44-01.920503.json,1791391279.1805806,1 +v2anneal_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cc34927b47_2026-10-07T16-39-53.465329.json,1791391033.9176633,1 +v2anneal_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_bytes,none,0.88,0.032659863237109045,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cc34927b47_2026-10-07T16-39-53.465329.json,1791391033.9176633,1 +v2anneal_merge3_116k_120k,global_piqa_completions_slk_latn,0,lm-eval,vllm,,acc_norm,none,0.89,0.031446603773522014,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cc34927b47_2026-10-07T16-39-53.465329.json,1791391033.9176633,1 +v2anneal_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/22fe31f4ad_2026-10-07T16-35-37.663667.json,1791390782.1327782,1 +v2anneal_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_bytes,none,0.68,0.046882617226215076,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/22fe31f4ad_2026-10-07T16-35-37.663667.json,1791390782.1327782,1 +v2anneal_merge3_116k_120k,global_piqa_completions_slv_latn,0,lm-eval,vllm,,acc_norm,none,0.69,0.046482319871173176,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/22fe31f4ad_2026-10-07T16-35-37.663667.json,1791390782.1327782,1 +v2anneal_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/dc839ac36f_2026-10-07T16-07-32.003232.json,1791389087.3278549,1 +v2anneal_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_bytes,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/dc839ac36f_2026-10-07T16-07-32.003232.json,1791389087.3278549,1 +v2anneal_merge3_116k_120k,global_piqa_completions_spa_latn_spai,0,lm-eval,vllm,,acc_norm,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/dc839ac36f_2026-10-07T16-07-32.003232.json,1791389087.3278549,1 +v2anneal_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc,none,0.9,0.03015113445777636,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/723fa69816_2026-10-07T16-37-39.426328.json,1791390899.9299471,1 +v2anneal_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.93,0.02564323999762428,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/723fa69816_2026-10-07T16-37-39.426328.json,1791390899.9299471,1 +v2anneal_merge3_116k_120k,global_piqa_completions_srp_cyrl,0,lm-eval,vllm,,acc_norm,none,0.92,0.027265992434429072,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/723fa69816_2026-10-07T16-37-39.426328.json,1791390899.9299471,1 +v2anneal_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc,none,0.86,0.0348735088019777,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c93826e2aa_2026-10-07T16-17-49.271465.json,1791389692.8769255,1 +v2anneal_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c93826e2aa_2026-10-07T16-17-49.271465.json,1791389692.8769255,1 +v2anneal_merge3_116k_120k,global_piqa_completions_swe_latn,0,lm-eval,vllm,,acc_norm,none,0.85,0.03588702812826367,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c93826e2aa_2026-10-07T16-17-49.271465.json,1791389692.8769255,1 +v2anneal_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc,none,0.6,0.0492365963917331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/74ec333d3e_2026-10-07T16-17-26.841022.json,1791389684.299938,1 +v2anneal_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_bytes,none,0.75,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/74ec333d3e_2026-10-07T16-17-26.841022.json,1791389684.299938,1 +v2anneal_merge3_116k_120k,global_piqa_completions_tur_latn,0,lm-eval,vllm,,acc_norm,none,0.74,0.0440844002276808,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/74ec333d3e_2026-10-07T16-17-26.841022.json,1791389684.299938,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc,none,0.84,0.03684529491774706,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9b481c4add_2026-10-07T16-35-38.404785.json,1791390782.7006094,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_bytes,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9b481c4add_2026-10-07T16-35-38.404785.json,1791390782.7006094,1 +v2anneal_merge3_116k_120k,global_piqa_completions_ukr_cyrl,0,lm-eval,vllm,,acc_norm,none,0.87,0.033799766898963114,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9b481c4add_2026-10-07T16-35-38.404785.json,1791390782.7006094,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_als_latn,0,lm-eval,vllm,,exact_match,strict_match,0.29,0.045604802157206845,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/89fda25c5d_2026-10-07T16-33-54.954750.json,1791390660.5386603,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_bos_latn,0,lm-eval,vllm,,exact_match,strict_match,0.48,0.050211673156867795,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/42849f77d6_2026-10-07T16-07-14.383308.json,1791389066.1690946,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_bul_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.55,0.04999999999999999,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0a8c24f968_2026-10-07T16-23-35.548147.json,1791390053.2589276,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_cat_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.04943110704237102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4b4fe4bb78_2026-10-07T16-21-39.054077.json,1791389934.62264,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_ces_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.04960449637488584,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fece9a69e7_2026-10-07T16-27-39.333965.json,1791390291.222766,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_deu_latn,0,lm-eval,vllm,,exact_match,strict_match,0.44,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ac0166c796_2026-10-07T16-19-28.392321.json,1791389804.3302152,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_ekk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.31,0.04648231987117316,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/303fa3c42a_2026-10-07T16-17-41.587992.json,1791389692.3847451,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_ell_grek,0,lm-eval,vllm,,exact_match,strict_match,0.25,0.04351941398892446,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/97b507a1de_2026-10-07T16-46-11.214054.json,1791391404.4603853,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_eng_latn,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f1ae51bda3_2026-10-07T16-07-23.474225.json,1791389083.6120522,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_fin_latn,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/88fc52318c_2026-10-07T16-13-33.389693.json,1791389444.578882,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_fra_latn_fran,0,lm-eval,vllm,,exact_match,strict_match,0.42,0.049604496374885836,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/27cf316a27_2026-10-07T16-07-10.905912.json,1791389070.724357,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_glg_latn,0,lm-eval,vllm,,exact_match,strict_match,0.35,0.047937248544110196,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6eee95f126_2026-10-07T16-19-27.509502.json,1791389807.5096474,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_hrv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.49,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4dd7ae9788_2026-10-07T16-29-50.621425.json,1791390423.6120315,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_hun_latn,0,lm-eval,vllm,,exact_match,strict_match,0.52,0.050211673156867795,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8b41b12284_2026-10-07T16-15-33.240431.json,1791389565.7358494,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_isl_latn,0,lm-eval,vllm,,exact_match,strict_match,0.56,0.04988876515698589,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7cc936fd02_2026-10-07T16-40-02.433038.json,1791391025.4957824,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_ita_latn,0,lm-eval,vllm,,exact_match,strict_match,0.44,0.049888765156985884,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/eea5f936b1_2026-10-07T16-19-43.438977.json,1791389813.9006722,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_kat_geor,0,lm-eval,vllm,,exact_match,strict_match,0.17,0.03775251680686371,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/082a9aa5d3_2026-10-07T16-17-32.622789.json,1791389682.8654413,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_lit_latn,0,lm-eval,vllm,,exact_match,strict_match,0.53,0.05016135580465919,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a499f67715_2026-10-07T16-31-43.152965.json,1791390536.6869774,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_mkd_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.52,0.050211673156867795,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2f9e21390c_2026-10-07T16-13-26.356241.json,1791389443.527353,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_nld_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.04943110704237102,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7682263751_2026-10-07T16-44-12.548837.json,1791391286.4623857,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_nno_latn,0,lm-eval,vllm,,exact_match,strict_match,0.45,0.05,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1644338021_2026-10-07T16-37-43.798634.json,1791390899.3934715,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_nob_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/09dc7c4d0e_2026-10-07T16-07-33.808045.json,1791389073.3461692,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_pol_latn,0,lm-eval,vllm,,exact_match,strict_match,0.37,0.04852365870939099,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e7bd676557_2026-10-07T16-07-25.732394.json,1791389071.0336287,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_por_latn_port,0,lm-eval,vllm,,exact_match,strict_match,0.51,0.05024183937956912,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/628147804b_2026-10-07T16-09-16.207809.json,1791389191.5722961,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_ron_latn,0,lm-eval,vllm,,exact_match,strict_match,0.38,0.04878317312145633,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d018925cc9_2026-10-07T16-44-05.545100.json,1791391277.463175,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_slk_latn,0,lm-eval,vllm,,exact_match,strict_match,0.41,0.049431107042371025,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e527401162_2026-10-07T16-21-32.666600.json,1791389930.5011594,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_slv_latn,0,lm-eval,vllm,,exact_match,strict_match,0.37,0.04852365870939098,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0371b55169_2026-10-07T16-21-33.020985.json,1791389927.6837442,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_spa_latn_spai,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d0749bd2d2_2026-10-07T16-13-40.226297.json,1791389438.7748606,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_srp_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/679026429a_2026-10-07T16-34-01.299762.json,1791390658.3919878,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_swe_latn,0,lm-eval,vllm,,exact_match,strict_match,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fe267d13bf_2026-10-07T16-09-19.713684.json,1791389190.895686,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_tur_latn,0,lm-eval,vllm,,exact_match,strict_match,0.47,0.050161355804659205,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7ecb056656_2026-10-07T16-19-28.217293.json,1791389804.2427118,1 +v2anneal_merge3_116k_120k,global_piqa_prompted_ukr_cyrl,0,lm-eval,vllm,,exact_match,strict_match,0.43,0.04975698519562428,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/43a67f226c_2026-10-07T16-07-27.095473.json,1791389083.6841066,1 +v2anneal_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,flexible-extract,0.8225928733889311,0.010522533016890798,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ee11240382_2026-10-07T16-18-41.302676.json,1791389690.836964,1 +v2anneal_merge3_116k_120k,gsm8k,4,lm-eval,vllm,,exact_match,strict-match,0.8188021228203184,0.010609827611527343,1319,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ee11240382_2026-10-07T16-18-41.302676.json,1791389690.836964,1 +v2anneal_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc,none,0.6088428599880502,0.004870121051762574,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cbbafbb1af_2026-10-07T16-08-42.529520.json,1791389069.1389947,1 +v2anneal_merge3_116k_120k,hellaswag,0,lm-eval,vllm,,acc_norm,none,0.7998406691894046,0.003993017173366916,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cbbafbb1af_2026-10-07T16-08-42.529520.json,1791389069.1389947,1 +v2anneal_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc,none,0.6323441545508863,0.0048118159593889594,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/219bfcff85_2026-10-07T16-20-10.366519.json,1791389441.3523157,1 +v2anneal_merge3_116k_120k,hellaswag,10,lm-eval,vllm,,acc_norm,none,0.8308105954989046,0.0037415289563157363,10042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/219bfcff85_2026-10-07T16-20-10.366519.json,1791389441.3523157,1 +v2anneal_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc,none,0.5073281945499946,0.005209469970023985,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b3ddae0e33_2026-10-07T16-33-14.964595.json,1791390534.749494,1 +v2anneal_merge3_116k_120k,hellaswag_ca,0,lm-eval,vllm,,acc_norm,none,0.6637715774617305,0.004922624654292291,9211,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b3ddae0e33_2026-10-07T16-33-14.964595.json,1791390534.749494,1 +v2anneal_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc,none,0.5377753895754971,0.0051688287475498956,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1e89f50b03_2026-10-07T16-14-49.230854.json,1791389436.6326294,1 +v2anneal_merge3_116k_120k,hellaswag_da,0,lm-eval,vllm,,acc_norm,none,0.6963997850617948,0.0047670038281279106,9305,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1e89f50b03_2026-10-07T16-14-49.230854.json,1791389436.6326294,1 +v2anneal_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc,none,0.5318104184457728,0.005155716553716665,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/94e9e90501_2026-10-07T16-08-33.713887.json,1791389069.5492256,1 +v2anneal_merge3_116k_120k,hellaswag_de,0,lm-eval,vllm,,acc_norm,none,0.6887275832621691,0.0047840289272060976,9368,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/94e9e90501_2026-10-07T16-08-33.713887.json,1791389069.5492256,1 +v2anneal_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc,none,0.5640068273949221,0.005122037059078281,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a3d2a9f1ee_2026-10-07T16-08-35.501008.json,1791389072.7848377,1 +v2anneal_merge3_116k_120k,hellaswag_es,0,lm-eval,vllm,,acc_norm,none,0.7368252613612118,0.004548466967345662,9374,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a3d2a9f1ee_2026-10-07T16-08-35.501008.json,1791389072.7848377,1 +v2anneal_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc,none,0.2997298757428417,0.004762478942364643,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/26c7814ef1_2026-10-07T16-45-25.092041.json,1791391276.122122,1 +v2anneal_merge3_116k_120k,hellaswag_eu,0,lm-eval,vllm,,acc_norm,none,0.3615343057806591,0.004994347913283903,9255,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/26c7814ef1_2026-10-07T16-45-25.092041.json,1791391276.122122,1 +v2anneal_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc,none,0.5538659241807667,0.005144359872065957,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/55ac4f7006_2026-10-07T16-06-46.709756.json,1791388945.0907815,1 +v2anneal_merge3_116k_120k,hellaswag_fr,0,lm-eval,vllm,,acc_norm,none,0.7245662882844293,0.004623213289578294,9338,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/55ac4f7006_2026-10-07T16-06-46.709756.json,1791388945.0907815,1 +v2anneal_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc,none,0.49540703199239783,0.005137794043051485,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/edf6445d7a_2026-10-07T16-29-06.085191.json,1791390289.0656593,1 +v2anneal_merge3_116k_120k,hellaswag_hr,0,lm-eval,vllm,,acc_norm,none,0.659592440080245,0.00486925415394992,9471,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/edf6445d7a_2026-10-07T16-29-06.085191.json,1791390289.0656593,1 +v2anneal_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc,none,0.4456629016339511,0.005205235942538942,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c315308f49_2026-10-07T16-35-12.091055.json,1791390656.8000557,1 +v2anneal_merge3_116k_120k,hellaswag_hu,0,lm-eval,vllm,,acc_norm,none,0.5808750959535037,0.0051672957392750445,9119,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c315308f49_2026-10-07T16-35-12.091055.json,1791390656.8000557,1 +v2anneal_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc,none,0.5348634830849559,0.005202435259696171,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4f08d13f15_2026-10-07T16-28-54.924314.json,1791390294.6461034,1 +v2anneal_merge3_116k_120k,hellaswag_it,0,lm-eval,vllm,,acc_norm,none,0.7065158272598716,0.0047495042695278366,9193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4f08d13f15_2026-10-07T16-28-54.924314.json,1791390294.6461034,1 +v2anneal_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc,none,0.5336211548839719,0.005183065143895703,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0c37c9421b_2026-10-07T16-28-58.283330.json,1791390292.795823,1 +v2anneal_merge3_116k_120k,hellaswag_nl,0,lm-eval,vllm,,acc_norm,none,0.6957366432811657,0.004780221178573865,9265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0c37c9421b_2026-10-07T16-28-58.283330.json,1791390292.795823,1 +v2anneal_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc,none,0.5456712536569509,0.00518318670554251,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8e1b7232b3_2026-10-07T16-23-04.665786.json,1791389930.7371392,1 +v2anneal_merge3_116k_120k,hellaswag_pt,0,lm-eval,vllm,,acc_norm,none,0.7196879401885361,0.004675620036763886,9229,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8e1b7232b3_2026-10-07T16-23-04.665786.json,1791389930.7371392,1 +v2anneal_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc,none,0.5151974040021633,0.0051980365983389796,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/daefc2edaa_2026-10-07T16-21-05.891255.json,1791389804.701976,1 +v2anneal_merge3_116k_120k,hellaswag_ro,0,lm-eval,vllm,,acc_norm,none,0.6707409410492158,0.004887832399513324,9245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/daefc2edaa_2026-10-07T16-21-05.891255.json,1791389804.701976,1 +v2anneal_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc,none,0.47158671586715867,0.005125920572235034,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/388afa6f28_2026-10-07T16-23-02.232842.json,1791389926.2247262,1 +v2anneal_merge3_116k_120k,hellaswag_sk,0,lm-eval,vllm,,acc_norm,none,0.6132841328413284,0.005000703295606996,9485,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/388afa6f28_2026-10-07T16-23-02.232842.json,1791389926.2247262,1 +v2anneal_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc,none,0.4981479521642502,0.005143954076315989,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/91e0c7eb37_2026-10-07T16-49-47.173871.json,1791391525.3839858,1 +v2anneal_merge3_116k_120k,hellaswag_sr,0,lm-eval,vllm,,acc_norm,none,0.6532966451476346,0.004896257995320515,9449,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/91e0c7eb37_2026-10-07T16-49-47.173871.json,1791391525.3839858,1 +v2anneal_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc,none,0.5315720236790178,0.005224939218682111,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6f3b7b8461_2026-10-07T16-33-19.693378.json,1791390550.7763617,1 +v2anneal_merge3_116k_120k,hellaswag_sv,0,lm-eval,vllm,,acc_norm,none,0.7037930278447709,0.004780781449127303,9122,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6f3b7b8461_2026-10-07T16-33-19.693378.json,1791390550.7763617,1 +v2anneal_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc,none,0.46625571261558085,0.005143160158369401,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2ab94cf30c_2026-10-07T16-45-47.769927.json,1791391286.567137,1 +v2anneal_merge3_116k_120k,hellaswag_uk,0,lm-eval,vllm,,acc_norm,none,0.6064406419385695,0.005036752570938245,9409,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2ab94cf30c_2026-10-07T16-45-47.769927.json,1791391286.567137,1 +v2anneal_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_loose_acc,none,0.434052757793765,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e9571d98ac_2026-10-07T16-11-01.635912.json,1791389203.477726,1 +v2anneal_merge3_116k_120k,ifeval,0,lm-eval,vllm,,inst_level_strict_acc,none,0.407673860911271,,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e9571d98ac_2026-10-07T16-11-01.635912.json,1791389203.477726,1 +v2anneal_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_loose_acc,none,0.2902033271719039,0.019530856691222623,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e9571d98ac_2026-10-07T16-11-01.635912.json,1791389203.477726,1 +v2anneal_merge3_116k_120k,ifeval,0,lm-eval,vllm,,prompt_level_strict_acc,none,0.266173752310536,0.019018766847290668,541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e9571d98ac_2026-10-07T16-11-01.635912.json,1791389203.477726,1 +v2anneal_merge3_116k_120k,include_base_44_albanian,0,lm-eval,vllm,yes,acc,none,0.7531760435571688,0.01841664141534992,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ac0a7d5e3f_2026-10-07T16-44-08.964754.json,1791391277.561087,1 +v2anneal_merge3_116k_120k,include_base_44_albanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.757847533632287,0.028751392398694772,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ac0a7d5e3f_2026-10-07T16-44-08.964754.json,1791391277.561087,1 +v2anneal_merge3_116k_120k,include_base_44_albanian_business_commerce,0,lm-eval,vllm,,acc,none,0.7533632286995515,0.028930413120910853,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ac0a7d5e3f_2026-10-07T16-44-08.964754.json,1791391277.561087,1 +v2anneal_merge3_116k_120k,include_base_44_albanian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ac0a7d5e3f_2026-10-07T16-44-08.964754.json,1791391277.561087,1 +v2anneal_merge3_116k_120k,include_base_44_albanian_social_science,0,lm-eval,vllm,,acc,none,0.8,0.05443310539518174,55,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ac0a7d5e3f_2026-10-07T16-44-08.964754.json,1791391277.561087,1 +v2anneal_merge3_116k_120k,include_base_44_albanian_stem,0,lm-eval,vllm,,acc,none,0.68,0.09521904571390467,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ac0a7d5e3f_2026-10-07T16-44-08.964754.json,1791391277.561087,1 +v2anneal_merge3_116k_120k,include_base_44_basque,0,lm-eval,vllm,yes,acc,none,0.446,0.022252153078595936,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/42253ac020_2026-10-07T16-46-06.395449.json,1791391403.1224623,1 +v2anneal_merge3_116k_120k,include_base_44_basque_professional_certification,0,lm-eval,vllm,,acc,none,0.446,0.022252153078595936,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/42253ac020_2026-10-07T16-46-06.395449.json,1791391403.1224623,1 +v2anneal_merge3_116k_120k,include_base_44_bulgarian,0,lm-eval,vllm,yes,acc,none,0.6927272727272727,0.01950185682981333,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1c6305f71e_2026-10-07T16-13-16.084881.json,1791389435.5616202,1 +v2anneal_merge3_116k_120k,include_base_44_bulgarian_arts_humanities,0,lm-eval,vllm,,acc,none,0.764,0.026909337594953852,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1c6305f71e_2026-10-07T16-13-16.084881.json,1791389435.5616202,1 +v2anneal_merge3_116k_120k,include_base_44_bulgarian_social_science,0,lm-eval,vllm,,acc,none,0.648,0.030266288057359866,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1c6305f71e_2026-10-07T16-13-16.084881.json,1791389435.5616202,1 +v2anneal_merge3_116k_120k,include_base_44_bulgarian_stem,0,lm-eval,vllm,,acc,none,0.56,0.07091242083423346,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1c6305f71e_2026-10-07T16-13-16.084881.json,1791389435.5616202,1 +v2anneal_merge3_116k_120k,include_base_44_croatian,0,lm-eval,vllm,yes,acc,none,0.7490909090909091,0.0184454871989235,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/556370b9d2_2026-10-07T16-07-09.631069.json,1791389066.7035391,1 +v2anneal_merge3_116k_120k,include_base_44_croatian_arts_humanities,0,lm-eval,vllm,,acc,none,0.708,0.028814320402205634,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/556370b9d2_2026-10-07T16-07-09.631069.json,1791389066.7035391,1 +v2anneal_merge3_116k_120k,include_base_44_croatian_social_science,0,lm-eval,vllm,,acc,none,0.796,0.025537121574548162,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/556370b9d2_2026-10-07T16-07-09.631069.json,1791389066.7035391,1 +v2anneal_merge3_116k_120k,include_base_44_croatian_stem,0,lm-eval,vllm,,acc,none,0.72,0.06414269805898185,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/556370b9d2_2026-10-07T16-07-09.631069.json,1791389066.7035391,1 +v2anneal_merge3_116k_120k,include_base_44_dutch,0,lm-eval,vllm,yes,acc,none,0.7168784029038112,0.0191140153498771,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/af001f5c55_2026-10-07T16-27-32.409476.json,1791390288.4328752,1 +v2anneal_merge3_116k_120k,include_base_44_dutch_applied_science,0,lm-eval,vllm,,acc,none,0.9333333333333333,0.06666666666666665,15,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/af001f5c55_2026-10-07T16-27-32.409476.json,1791390288.4328752,1 +v2anneal_merge3_116k_120k,include_base_44_dutch_arts_humanities,0,lm-eval,vllm,,acc,none,0.7366255144032922,0.028314085938532733,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/af001f5c55_2026-10-07T16-27-32.409476.json,1791390288.4328752,1 +v2anneal_merge3_116k_120k,include_base_44_dutch_health_oriented_education,0,lm-eval,vllm,,acc,none,0.52,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/af001f5c55_2026-10-07T16-27-32.409476.json,1791390288.4328752,1 +v2anneal_merge3_116k_120k,include_base_44_dutch_social_science,0,lm-eval,vllm,,acc,none,0.7119341563786008,0.029111066408470707,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/af001f5c55_2026-10-07T16-27-32.409476.json,1791390288.4328752,1 +v2anneal_merge3_116k_120k,include_base_44_dutch_stem,0,lm-eval,vllm,,acc,none,0.64,0.09797958971132711,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/af001f5c55_2026-10-07T16-27-32.409476.json,1791390288.4328752,1 +v2anneal_merge3_116k_120k,include_base_44_estonian,0,lm-eval,vllm,yes,acc,none,0.5848214285714286,0.03236006593644787,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7ce2ef7a4f_2026-10-07T16-09-09.865792.json,1791389187.8629825,1 +v2anneal_merge3_116k_120k,include_base_44_estonian_applied_science,0,lm-eval,vllm,,acc,none,0.9285714285714286,0.07142857142857144,14,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7ce2ef7a4f_2026-10-07T16-09-09.865792.json,1791389187.8629825,1 +v2anneal_merge3_116k_120k,include_base_44_estonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.5217391304347826,0.03949109157518468,161,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7ce2ef7a4f_2026-10-07T16-09-09.865792.json,1791389187.8629825,1 +v2anneal_merge3_116k_120k,include_base_44_estonian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5,0.5,2,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7ce2ef7a4f_2026-10-07T16-09-09.865792.json,1791389187.8629825,1 +v2anneal_merge3_116k_120k,include_base_44_estonian_social_science,0,lm-eval,vllm,,acc,none,0.6363636363636364,0.15212000482437738,11,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7ce2ef7a4f_2026-10-07T16-09-09.865792.json,1791389187.8629825,1 +v2anneal_merge3_116k_120k,include_base_44_estonian_stem,0,lm-eval,vllm,,acc,none,0.7222222222222222,0.07570946042991632,36,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7ce2ef7a4f_2026-10-07T16-09-09.865792.json,1791389187.8629825,1 +v2anneal_merge3_116k_120k,include_base_44_finnish,0,lm-eval,vllm,yes,acc,none,0.5190562613430127,0.021169162807102054,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d768a8f534_2026-10-07T16-09-11.711153.json,1791389188.675047,1 +v2anneal_merge3_116k_120k,include_base_44_finnish_applied_science,0,lm-eval,vllm,,acc,none,0.5172413793103449,0.09443492370778726,29,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d768a8f534_2026-10-07T16-09-11.711153.json,1791389188.675047,1 +v2anneal_merge3_116k_120k,include_base_44_finnish_arts_humanities,0,lm-eval,vllm,,acc,none,0.43805309734513276,0.033076516090319925,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d768a8f534_2026-10-07T16-09-11.711153.json,1791389188.675047,1 +v2anneal_merge3_116k_120k,include_base_44_finnish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6222222222222222,0.07309112127323451,45,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d768a8f534_2026-10-07T16-09-11.711153.json,1791389188.675047,1 +v2anneal_merge3_116k_120k,include_base_44_finnish_social_science,0,lm-eval,vllm,,acc,none,0.5707964601769911,0.03299749897771093,226,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d768a8f534_2026-10-07T16-09-11.711153.json,1791389188.675047,1 +v2anneal_merge3_116k_120k,include_base_44_finnish_stem,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d768a8f534_2026-10-07T16-09-11.711153.json,1791389188.675047,1 +v2anneal_merge3_116k_120k,include_base_44_french,0,lm-eval,vllm,yes,acc,none,0.5918854415274463,0.023652101764873208,419,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f24b9cb035_2026-10-07T16-29-40.643580.json,1791390418.0957553,1 +v2anneal_merge3_116k_120k,include_base_44_french_arts_humanities,0,lm-eval,vllm,,acc,none,0.6578947368421053,0.029143059763315174,266,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f24b9cb035_2026-10-07T16-29-40.643580.json,1791390418.0957553,1 +v2anneal_merge3_116k_120k,include_base_44_french_driving_license,0,lm-eval,vllm,,acc,none,0.3829787234042553,0.0716734777251339,47,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f24b9cb035_2026-10-07T16-29-40.643580.json,1791390418.0957553,1 +v2anneal_merge3_116k_120k,include_base_44_french_health_oriented_education,0,lm-eval,vllm,,acc,none,0.5625,0.128086884574495,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f24b9cb035_2026-10-07T16-29-40.643580.json,1791390418.0957553,1 +v2anneal_merge3_116k_120k,include_base_44_french_social_science,0,lm-eval,vllm,,acc,none,0.5405405405405406,0.0583278951301236,74,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f24b9cb035_2026-10-07T16-29-40.643580.json,1791390418.0957553,1 +v2anneal_merge3_116k_120k,include_base_44_french_stem,0,lm-eval,vllm,,acc,none,0.375,0.125,16,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f24b9cb035_2026-10-07T16-29-40.643580.json,1791390418.0957553,1 +v2anneal_merge3_116k_120k,include_base_44_georgian,0,lm-eval,vllm,yes,acc,none,0.46,0.022311333245289593,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6932e08718_2026-10-07T16-17-36.459975.json,1791389684.4858003,1 +v2anneal_merge3_116k_120k,include_base_44_georgian_arts_humanities,0,lm-eval,vllm,,acc,none,0.46,0.022311333245289593,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6932e08718_2026-10-07T16-17-36.459975.json,1791389684.4858003,1 +v2anneal_merge3_116k_120k,include_base_44_german,0,lm-eval,vllm,yes,acc,none,0.539568345323741,0.042656146188785785,139,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/269ddac164_2026-10-07T16-21-31.851028.json,1791389931.202228,1 +v2anneal_merge3_116k_120k,include_base_44_german_driving_license,0,lm-eval,vllm,,acc,none,0.5217391304347826,0.10649955403405124,23,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/269ddac164_2026-10-07T16-21-31.851028.json,1791389931.202228,1 +v2anneal_merge3_116k_120k,include_base_44_german_social_science,0,lm-eval,vllm,,acc,none,0.5604395604395604,0.052318156985661904,91,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/269ddac164_2026-10-07T16-21-31.851028.json,1791389931.202228,1 +v2anneal_merge3_116k_120k,include_base_44_german_stem,0,lm-eval,vllm,,acc,none,0.48,0.10198039027185571,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/269ddac164_2026-10-07T16-21-31.851028.json,1791389931.202228,1 +v2anneal_merge3_116k_120k,include_base_44_greek,0,lm-eval,vllm,yes,acc,none,0.5561594202898551,0.021045535116615995,552,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0015a357e9_2026-10-07T16-37-46.755272.json,1791390899.9159665,1 +v2anneal_merge3_116k_120k,include_base_44_greek_arts_humanities,0,lm-eval,vllm,,acc,none,0.6216216216216216,0.08083044344561424,37,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0015a357e9_2026-10-07T16-37-46.755272.json,1791390899.9159665,1 +v2anneal_merge3_116k_120k,include_base_44_greek_business_commerce,0,lm-eval,vllm,,acc,none,0.7142857142857143,0.057372809207321344,63,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0015a357e9_2026-10-07T16-37-46.755272.json,1791390899.9159665,1 +v2anneal_merge3_116k_120k,include_base_44_greek_health_oriented_education,0,lm-eval,vllm,,acc,none,0.4,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0015a357e9_2026-10-07T16-37-46.755272.json,1791390899.9159665,1 +v2anneal_merge3_116k_120k,include_base_44_greek_medical_license,0,lm-eval,vllm,,acc,none,0.5223880597014925,0.043312014931941,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0015a357e9_2026-10-07T16-37-46.755272.json,1791390899.9159665,1 +v2anneal_merge3_116k_120k,include_base_44_greek_professional_certification,0,lm-eval,vllm,,acc,none,0.5,0.043355498476206004,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0015a357e9_2026-10-07T16-37-46.755272.json,1791390899.9159665,1 +v2anneal_merge3_116k_120k,include_base_44_greek_social_science,0,lm-eval,vllm,,acc,none,0.5746268656716418,0.04286987049655245,134,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0015a357e9_2026-10-07T16-37-46.755272.json,1791390899.9159665,1 +v2anneal_merge3_116k_120k,include_base_44_greek_stem,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0015a357e9_2026-10-07T16-37-46.755272.json,1791390899.9159665,1 +v2anneal_merge3_116k_120k,include_base_44_hungarian,0,lm-eval,vllm,yes,acc,none,0.4672727272727273,0.021326044276011657,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/abc1bdb5f0_2026-10-07T16-40-07.380452.json,1791391038.4627116,1 +v2anneal_merge3_116k_120k,include_base_44_hungarian_applied_science,0,lm-eval,vllm,,acc,none,0.4604105571847507,0.027031173508158517,341,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/abc1bdb5f0_2026-10-07T16-40-07.380452.json,1791391038.4627116,1 +v2anneal_merge3_116k_120k,include_base_44_hungarian_social_science,0,lm-eval,vllm,,acc,none,0.483695652173913,0.03694140747212635,184,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/abc1bdb5f0_2026-10-07T16-40-07.380452.json,1791391038.4627116,1 +v2anneal_merge3_116k_120k,include_base_44_hungarian_stem,0,lm-eval,vllm,,acc,none,0.44,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/abc1bdb5f0_2026-10-07T16-40-07.380452.json,1791391038.4627116,1 +v2anneal_merge3_116k_120k,include_base_44_italian,0,lm-eval,vllm,yes,acc,none,0.7135036496350365,0.019281207384359775,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c77679cfe3_2026-10-07T16-13-15.624067.json,1791389435.7112331,1 +v2anneal_merge3_116k_120k,include_base_44_italian_applied_science,0,lm-eval,vllm,,acc,none,0.7714285714285715,0.0720144043214405,35,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c77679cfe3_2026-10-07T16-13-15.624067.json,1791389435.7112331,1 +v2anneal_merge3_116k_120k,include_base_44_italian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6646706586826348,0.03664249082074466,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c77679cfe3_2026-10-07T16-13-15.624067.json,1791389435.7112331,1 +v2anneal_merge3_116k_120k,include_base_44_italian_health_oriented_education,0,lm-eval,vllm,,acc,none,0.75,0.1305582419667734,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c77679cfe3_2026-10-07T16-13-15.624067.json,1791389435.7112331,1 +v2anneal_merge3_116k_120k,include_base_44_italian_professional_certification,0,lm-eval,vllm,,acc,none,0.6774193548387096,0.03766930374975111,155,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c77679cfe3_2026-10-07T16-13-15.624067.json,1791389435.7112331,1 +v2anneal_merge3_116k_120k,include_base_44_italian_social_science,0,lm-eval,vllm,,acc,none,0.7844311377245509,0.031916582528798025,167,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c77679cfe3_2026-10-07T16-13-15.624067.json,1791389435.7112331,1 +v2anneal_merge3_116k_120k,include_base_44_italian_stem,0,lm-eval,vllm,,acc,none,0.6666666666666666,0.1421338109037403,12,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c77679cfe3_2026-10-07T16-13-15.624067.json,1791389435.7112331,1 +v2anneal_merge3_116k_120k,include_base_44_lithuanian,0,lm-eval,vllm,yes,acc,none,0.6198501872659176,0.020853045530664936,534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b5035cd8a2_2026-10-07T16-13-23.300527.json,1791389443.0246785,1 +v2anneal_merge3_116k_120k,include_base_44_lithuanian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6149253731343284,0.026626275719904603,335,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b5035cd8a2_2026-10-07T16-13-23.300527.json,1791389443.0246785,1 +v2anneal_merge3_116k_120k,include_base_44_lithuanian_business_commerce,0,lm-eval,vllm,,acc,none,0.425,0.07915823166939519,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b5035cd8a2_2026-10-07T16-13-23.300527.json,1791389443.0246785,1 +v2anneal_merge3_116k_120k,include_base_44_lithuanian_professional_certification,0,lm-eval,vllm,,acc,none,0.6458333333333334,0.06976139255528774,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b5035cd8a2_2026-10-07T16-13-23.300527.json,1791389443.0246785,1 +v2anneal_merge3_116k_120k,include_base_44_lithuanian_social_science,0,lm-eval,vllm,,acc,none,0.6363636363636364,0.05517972533335309,77,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b5035cd8a2_2026-10-07T16-13-23.300527.json,1791389443.0246785,1 +v2anneal_merge3_116k_120k,include_base_44_lithuanian_stem,0,lm-eval,vllm,,acc,none,0.8235294117647058,0.06636189115503133,34,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b5035cd8a2_2026-10-07T16-13-23.300527.json,1791389443.0246785,1 +v2anneal_merge3_116k_120k,include_base_44_north macedonian,0,lm-eval,vllm,yes,acc,none,0.8185117967332124,0.016314313091005606,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ff28fd3983_2026-10-07T16-09-11.122921.json,1791389192.8647738,1 +v2anneal_merge3_116k_120k,include_base_44_north macedonian_arts_humanities,0,lm-eval,vllm,,acc,none,0.8616071428571429,0.023123791858848813,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ff28fd3983_2026-10-07T16-09-11.122921.json,1791389192.8647738,1 +v2anneal_merge3_116k_120k,include_base_44_north macedonian_business_commerce,0,lm-eval,vllm,,acc,none,0.7946428571428571,0.027051320329065504,224,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ff28fd3983_2026-10-07T16-09-11.122921.json,1791389192.8647738,1 +v2anneal_merge3_116k_120k,include_base_44_north macedonian_social_science,0,lm-eval,vllm,,acc,none,0.8679245283018868,0.046951599766681604,53,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ff28fd3983_2026-10-07T16-09-11.122921.json,1791389192.8647738,1 +v2anneal_merge3_116k_120k,include_base_44_north macedonian_stem,0,lm-eval,vllm,,acc,none,0.68,0.06663945022680344,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ff28fd3983_2026-10-07T16-09-11.122921.json,1791389192.8647738,1 +v2anneal_merge3_116k_120k,include_base_44_polish,0,lm-eval,vllm,yes,acc,none,0.5328467153284672,0.02128068000579209,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/78c6562782_2026-10-07T16-44-00.990346.json,1791391275.8303728,1 +v2anneal_merge3_116k_120k,include_base_44_polish_professional_certification,0,lm-eval,vllm,,acc,none,0.5443548387096774,0.0223847282122757,496,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/78c6562782_2026-10-07T16-44-00.990346.json,1791391275.8303728,1 +v2anneal_merge3_116k_120k,include_base_44_polish_social_science,0,lm-eval,vllm,,acc,none,0.75,0.25,4,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/78c6562782_2026-10-07T16-44-00.990346.json,1791391275.8303728,1 +v2anneal_merge3_116k_120k,include_base_44_polish_stem,0,lm-eval,vllm,,acc,none,0.3958333333333333,0.07133220238382322,48,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/78c6562782_2026-10-07T16-44-00.990346.json,1791391275.8303728,1 +v2anneal_merge3_116k_120k,include_base_44_portuguese,0,lm-eval,vllm,yes,acc,none,0.6007259528130672,0.020570828679776734,551,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6b1e6eb56f_2026-10-07T16-35-51.118512.json,1791390788.8467321,1 +v2anneal_merge3_116k_120k,include_base_44_portuguese_applied_science,0,lm-eval,vllm,,acc,none,0.4880952380952381,0.05486657163025336,84,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6b1e6eb56f_2026-10-07T16-35-51.118512.json,1791390788.8467321,1 +v2anneal_merge3_116k_120k,include_base_44_portuguese_arts_humanities,0,lm-eval,vllm,,acc,none,0.6298701298701299,0.03903524043561298,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6b1e6eb56f_2026-10-07T16-35-51.118512.json,1791390788.8467321,1 +v2anneal_merge3_116k_120k,include_base_44_portuguese_business_commerce,0,lm-eval,vllm,,acc,none,0.4583333333333333,0.05913268547421808,72,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6b1e6eb56f_2026-10-07T16-35-51.118512.json,1791390788.8467321,1 +v2anneal_merge3_116k_120k,include_base_44_portuguese_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6612903225806451,0.060596141174796975,62,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6b1e6eb56f_2026-10-07T16-35-51.118512.json,1791390788.8467321,1 +v2anneal_merge3_116k_120k,include_base_44_portuguese_social_science,0,lm-eval,vllm,,acc,none,0.7012987012987013,0.0370019283065312,154,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6b1e6eb56f_2026-10-07T16-35-51.118512.json,1791390788.8467321,1 +v2anneal_merge3_116k_120k,include_base_44_portuguese_stem,0,lm-eval,vllm,,acc,none,0.44,0.10132456102380442,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6b1e6eb56f_2026-10-07T16-35-51.118512.json,1791390788.8467321,1 +v2anneal_merge3_116k_120k,include_base_44_serbian,0,lm-eval,vllm,yes,acc,none,0.6709090909090909,0.019924278165740845,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e130eb6765_2026-10-07T16-11-26.377046.json,1791389325.5139508,1 +v2anneal_merge3_116k_120k,include_base_44_serbian_arts_humanities,0,lm-eval,vllm,,acc,none,0.6421725239616614,0.02713847286994475,313,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e130eb6765_2026-10-07T16-11-26.377046.json,1791389325.5139508,1 +v2anneal_merge3_116k_120k,include_base_44_serbian_social_science,0,lm-eval,vllm,,acc,none,0.7486631016042781,0.031806425764228506,187,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e130eb6765_2026-10-07T16-11-26.377046.json,1791389325.5139508,1 +v2anneal_merge3_116k_120k,include_base_44_serbian_stem,0,lm-eval,vllm,,acc,none,0.56,0.07091242083423346,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e130eb6765_2026-10-07T16-11-26.377046.json,1791389325.5139508,1 +v2anneal_merge3_116k_120k,include_base_44_spanish,0,lm-eval,vllm,yes,acc,none,0.6654545454545454,0.019866018087645914,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fcfb2ce214_2026-10-07T16-21-32.727378.json,1791389935.248816,1 +v2anneal_merge3_116k_120k,include_base_44_spanish_arts_humanities,0,lm-eval,vllm,,acc,none,0.58,0.03127799950463661,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fcfb2ce214_2026-10-07T16-21-32.727378.json,1791389935.248816,1 +v2anneal_merge3_116k_120k,include_base_44_spanish_health_oriented_education,0,lm-eval,vllm,,acc,none,0.6,0.1,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fcfb2ce214_2026-10-07T16-21-32.727378.json,1791389935.248816,1 +v2anneal_merge3_116k_120k,include_base_44_spanish_social_science,0,lm-eval,vllm,,acc,none,0.744,0.027657108718204846,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fcfb2ce214_2026-10-07T16-21-32.727378.json,1791389935.248816,1 +v2anneal_merge3_116k_120k,include_base_44_spanish_stem,0,lm-eval,vllm,,acc,none,0.8,0.08164965809277261,25,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/fcfb2ce214_2026-10-07T16-21-32.727378.json,1791389935.248816,1 +v2anneal_merge3_116k_120k,include_base_44_turkish,0,lm-eval,vllm,yes,acc,none,0.5675182481751825,0.02069219384437295,548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/939cede867_2026-10-07T16-17-34.791940.json,1791389691.2702806,1 +v2anneal_merge3_116k_120k,include_base_44_turkish_arts_humanities,0,lm-eval,vllm,,acc,none,0.536144578313253,0.038823108508905954,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/939cede867_2026-10-07T16-17-34.791940.json,1791389691.2702806,1 +v2anneal_merge3_116k_120k,include_base_44_turkish_business_commerce,0,lm-eval,vllm,,acc,none,0.7168674698795181,0.035072954313705176,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/939cede867_2026-10-07T16-17-34.791940.json,1791389691.2702806,1 +v2anneal_merge3_116k_120k,include_base_44_turkish_social_science,0,lm-eval,vllm,,acc,none,0.5180722891566265,0.03889951252827222,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/939cede867_2026-10-07T16-17-34.791940.json,1791389691.2702806,1 +v2anneal_merge3_116k_120k,include_base_44_turkish_stem,0,lm-eval,vllm,,acc,none,0.34,0.0676726816132972,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/939cede867_2026-10-07T16-17-34.791940.json,1791389691.2702806,1 +v2anneal_merge3_116k_120k,include_base_44_ukrainian,0,lm-eval,vllm,yes,acc,none,0.6236363636363637,0.02069909943212459,550,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/961e3743c1_2026-10-07T16-31-44.734271.json,1791390538.4425557,1 +v2anneal_merge3_116k_120k,include_base_44_ukrainian_arts_humanities,0,lm-eval,vllm,,acc,none,0.608,0.030938207620401222,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/961e3743c1_2026-10-07T16-31-44.734271.json,1791390538.4425557,1 +v2anneal_merge3_116k_120k,include_base_44_ukrainian_social_science,0,lm-eval,vllm,,acc,none,0.644,0.0303436806571532,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/961e3743c1_2026-10-07T16-31-44.734271.json,1791390538.4425557,1 +v2anneal_merge3_116k_120k,include_base_44_ukrainian_stem,0,lm-eval,vllm,,acc,none,0.6,0.06998542122237651,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/961e3743c1_2026-10-07T16-31-44.734271.json,1791390538.4425557,1 +v2anneal_merge3_116k_120k,jeopardy,10,lm-eval,vllm,,exact_match,strict-match,0.5351913084553613,0.010842609441179162,2117,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0c429ee36e_2026-10-07T16-44-33.492272.json,1791391284.838968,1 +v2anneal_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,acc,none,0.7349117019212109,0.006149289402157839,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6f9643342d_2026-10-07T16-44-25.528844.json,1791391280.8735526,1 +v2anneal_merge3_116k_120k,lambada_openai,0,lm-eval,vllm,,perplexity,none,3.509484352053441,0.06962498037378043,5153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6f9643342d_2026-10-07T16-44-25.528844.json,1791391280.8735526,1 +v2anneal_merge3_116k_120k,mbpp,3,lm-eval,vllm,,pass_at_1,none,0.614,0.02179352921928117,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cbb7b22100_2026-10-07T16-36-27.692616.json,1791390780.3749652,1 +v2anneal_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,flexible-extract,0.692,0.029256928606501864,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3d346596a9_2026-10-07T16-39-32.988919.json,1791390992.4948301,1 +v2anneal_merge3_116k_120k,mgsm_native_cot_de,5,lm-eval,vllm,,exact_match,strict-match,0.712,0.02869700458739821,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3d346596a9_2026-10-07T16-39-32.988919.json,1791390992.4948301,1 +v2anneal_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,flexible-extract,0.864,0.02172334261705206,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/380cf2af22_2026-10-07T16-13-31.126075.json,1791389442.998439,1 +v2anneal_merge3_116k_120k,mgsm_native_cot_en,5,lm-eval,vllm,,exact_match,strict-match,0.812,0.024760377727750495,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/380cf2af22_2026-10-07T16-13-31.126075.json,1791389442.998439,1 +v2anneal_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,flexible-extract,0.824,0.024133497525457112,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/19a2140484_2026-10-07T16-36-01.353049.json,1791390785.2512228,1 +v2anneal_merge3_116k_120k,mgsm_native_cot_es,5,lm-eval,vllm,,exact_match,strict-match,0.756,0.027217995464553182,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/19a2140484_2026-10-07T16-36-01.353049.json,1791390785.2512228,1 +v2anneal_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,flexible-extract,0.684,0.02946265759857869,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/bdf2af37dc_2026-10-07T16-48-23.750844.json,1791391523.450797,1 +v2anneal_merge3_116k_120k,mgsm_native_cot_fr,5,lm-eval,vllm,,exact_match,strict-match,0.724,0.028328537274211335,250,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/bdf2af37dc_2026-10-07T16-48-23.750844.json,1791391523.450797,1 +v2anneal_merge3_116k_120k,mmlu,5,lm-eval,vllm,yes,acc,none,0.7281014100555476,0.003599573086885292,14042,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_abstract_algebra,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_anatomy,5,lm-eval,vllm,,acc,none,0.6370370370370371,0.041539484047424,135,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_astronomy,5,lm-eval,vllm,,acc,none,0.8092105263157895,0.03197565821032503,152,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_business_ethics,5,lm-eval,vllm,,acc,none,0.73,0.04461960433384737,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_clinical_knowledge,5,lm-eval,vllm,,acc,none,0.7433962264150943,0.02688064788905203,265,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_college_biology,5,lm-eval,vllm,,acc,none,0.8680555555555556,0.02830096838204442,144,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_college_chemistry,5,lm-eval,vllm,,acc,none,0.5,0.050251890762960605,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_college_computer_science,5,lm-eval,vllm,,acc,none,0.71,0.045604802157206865,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_college_mathematics,5,lm-eval,vllm,,acc,none,0.54,0.05009082659620331,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_college_medicine,5,lm-eval,vllm,,acc,none,0.7109826589595376,0.03456425745086997,173,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_college_physics,5,lm-eval,vllm,,acc,none,0.5294117647058824,0.04966570903978531,102,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_computer_security,5,lm-eval,vllm,,acc,none,0.81,0.039427724440366255,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_conceptual_physics,5,lm-eval,vllm,,acc,none,0.7914893617021277,0.026556982117838728,235,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_econometrics,5,lm-eval,vllm,,acc,none,0.5877192982456141,0.046306532033665936,114,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_electrical_engineering,5,lm-eval,vllm,,acc,none,0.7310344827586207,0.03695183311650232,145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_elementary_mathematics,5,lm-eval,vllm,,acc,none,0.6507936507936508,0.024552292209342713,378,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_formal_logic,5,lm-eval,vllm,,acc,none,0.6349206349206349,0.04306241259127154,126,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_global_facts,5,lm-eval,vllm,,acc,none,0.48,0.05021167315686783,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_biology,5,lm-eval,vllm,,acc,none,0.8709677419354839,0.01907088925479277,310,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_chemistry,5,lm-eval,vllm,,acc,none,0.6798029556650246,0.032826493853041455,203,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_computer_science,5,lm-eval,vllm,,acc,none,0.8,0.04020151261036849,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_european_history,5,lm-eval,vllm,,acc,none,0.8303030303030303,0.02931118867498314,165,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_geography,5,lm-eval,vllm,,acc,none,0.8838383838383839,0.02282888177524936,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_government_and_politics,5,lm-eval,vllm,,acc,none,0.9585492227979274,0.01438543285747641,193,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_macroeconomics,5,lm-eval,vllm,,acc,none,0.7871794871794872,0.020752423722128037,390,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_mathematics,5,lm-eval,vllm,,acc,none,0.5185185185185185,0.03046462171889531,270,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_microeconomics,5,lm-eval,vllm,,acc,none,0.8739495798319328,0.021559623121213883,238,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_physics,5,lm-eval,vllm,,acc,none,0.5629139072847682,0.040500357222306375,151,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_psychology,5,lm-eval,vllm,,acc,none,0.9100917431192661,0.012264304540230489,545,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_statistics,5,lm-eval,vllm,,acc,none,0.6944444444444444,0.0314155462940254,216,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_us_history,5,lm-eval,vllm,,acc,none,0.8774509803921569,0.023015389732458234,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_high_school_world_history,5,lm-eval,vllm,,acc,none,0.8818565400843882,0.021011052659878477,237,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_human_aging,5,lm-eval,vllm,,acc,none,0.7713004484304933,0.028188240046929196,223,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_human_sexuality,5,lm-eval,vllm,,acc,none,0.8396946564885496,0.032178294207446285,131,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_humanities,5,lm-eval,vllm,yes,acc,none,0.6839532412327312,0.0065028381537749385,4705,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_international_law,5,lm-eval,vllm,,acc,none,0.8429752066115702,0.03321244842547127,121,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_jurisprudence,5,lm-eval,vllm,,acc,none,0.8240740740740741,0.036809181416738786,108,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_logical_fallacies,5,lm-eval,vllm,,acc,none,0.7975460122699386,0.031570650789119054,163,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_machine_learning,5,lm-eval,vllm,,acc,none,0.6160714285714286,0.04616143075028549,112,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_management,5,lm-eval,vllm,,acc,none,0.8252427184466019,0.03760178006026618,103,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_marketing,5,lm-eval,vllm,,acc,none,0.8931623931623932,0.02023714900899092,234,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_medical_genetics,5,lm-eval,vllm,,acc,none,0.76,0.04292346959909278,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_miscellaneous,5,lm-eval,vllm,,acc,none,0.8314176245210728,0.013387895731543545,783,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_moral_disputes,5,lm-eval,vllm,,acc,none,0.7947976878612717,0.021742519835276364,346,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_moral_scenarios,5,lm-eval,vllm,,acc,none,0.553072625698324,0.016628030039647648,895,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_nutrition,5,lm-eval,vllm,,acc,none,0.7581699346405228,0.024518195641879306,306,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_other,5,lm-eval,vllm,yes,acc,none,0.7409076279369167,0.007613190315254586,3107,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_philosophy,5,lm-eval,vllm,,acc,none,0.7588424437299035,0.024296594034763443,311,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_prehistory,5,lm-eval,vllm,,acc,none,0.845679012345679,0.02010083099985096,324,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_professional_accounting,5,lm-eval,vllm,,acc,none,0.5283687943262412,0.029779450957303062,282,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_professional_law,5,lm-eval,vllm,,acc,none,0.5658409387222947,0.012659033237067257,1534,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_professional_medicine,5,lm-eval,vllm,,acc,none,0.7242647058823529,0.02714627193662515,272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_professional_psychology,5,lm-eval,vllm,,acc,none,0.7467320261437909,0.017593486895366887,612,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_public_relations,5,lm-eval,vllm,,acc,none,0.7181818181818181,0.043091187099464606,110,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_security_studies,5,lm-eval,vllm,,acc,none,0.7836734693877551,0.026358916334903996,245,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_social_sciences,5,lm-eval,vllm,yes,acc,none,0.8254793630159246,0.0066831673169256076,3077,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_sociology,5,lm-eval,vllm,,acc,none,0.8606965174129353,0.024484487162913997,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_stem,5,lm-eval,vllm,yes,acc,none,0.6863304789089756,0.008000624435611624,3153,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_us_foreign_policy,5,lm-eval,vllm,,acc,none,0.91,0.028762349126466136,100,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_virology,5,lm-eval,vllm,,acc,none,0.5421686746987951,0.038786267710023595,166,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,mmlu_world_religions,5,lm-eval,vllm,,acc,none,0.8421052631578947,0.027966785859160903,171,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bc5b4e4f9_2026-10-07T16-26-35.637393.json,1791390049.502288,1 +v2anneal_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc,none,0.98413344182262,0.002520958990620561,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/179749832a_2026-10-07T16-11-33.713743.json,1791389327.5481622,1 +v2anneal_merge3_116k_120k,multiblimp_bul,0,lm-eval,vllm,,acc_norm,none,0.9755899104963385,0.0031132626238845732,2458,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/179749832a_2026-10-07T16-11-33.713743.json,1791389327.5481622,1 +v2anneal_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc,none,0.9772329246935202,0.0031217614380178514,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5713453a47_2026-10-07T16-13-31.572848.json,1791389443.0665486,1 +v2anneal_merge3_116k_120k,multiblimp_cat,0,lm-eval,vllm,,acc_norm,none,0.9767950963222417,0.003150929343267722,2284,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5713453a47_2026-10-07T16-13-31.572848.json,1791389443.0665486,1 +v2anneal_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc,none,0.950187969924812,0.003335201691876205,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4dca620c5b_2026-10-07T16-40-15.559111.json,1791391032.115113,1 +v2anneal_merge3_116k_120k,multiblimp_ces,0,lm-eval,vllm,,acc_norm,none,0.9546522556390977,0.003189706064952456,4256,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4dca620c5b_2026-10-07T16-40-15.559111.json,1791391032.115113,1 +v2anneal_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a68425aace_2026-10-07T16-43-39.607844.json,1791391278.051833,1 +v2anneal_merge3_116k_120k,multiblimp_dan,0,lm-eval,vllm,,acc_norm,none,1.0,0.0,50,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a68425aace_2026-10-07T16-43-39.607844.json,1791391278.051833,1 +v2anneal_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc,none,0.9860748476936466,0.002444974984100428,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5a960cf6db_2026-10-07T16-31-46.755921.json,1791390543.2573829,1 +v2anneal_merge3_116k_120k,multiblimp_deu,0,lm-eval,vllm,,acc_norm,none,0.9856396866840731,0.0024823359170968846,2298,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5a960cf6db_2026-10-07T16-31-46.755921.json,1791390543.2573829,1 +v2anneal_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc,none,0.9963503649635036,0.001822316053716181,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/03834f0feb_2026-10-07T16-05-01.529277.json,1791388947.8835294,1 +v2anneal_merge3_116k_120k,multiblimp_ell,0,lm-eval,vllm,,acc_norm,none,0.9972627737226277,0.0015788944371116819,1096,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/03834f0feb_2026-10-07T16-05-01.529277.json,1791388947.8835294,1 +v2anneal_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc,none,0.9922077922077922,0.003170796786706597,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/41f003f2ef_2026-10-07T16-27-15.201697.json,1791390293.1578467,1 +v2anneal_merge3_116k_120k,multiblimp_eng,0,lm-eval,vllm,,acc_norm,none,0.9922077922077922,0.003170796786706597,770,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/41f003f2ef_2026-10-07T16-27-15.201697.json,1791390293.1578467,1 +v2anneal_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc,none,0.9040776699029126,0.005804415056117212,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/746530fdb4_2026-10-07T16-09-15.464147.json,1791389191.0115395,1 +v2anneal_merge3_116k_120k,multiblimp_est,0,lm-eval,vllm,,acc_norm,none,0.9025242718446602,0.005846196625735597,2575,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/746530fdb4_2026-10-07T16-09-15.464147.json,1791389191.0115395,1 +v2anneal_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc,none,0.9487179487179487,0.0133741688167181,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/361b029fb7_2026-10-07T16-27-19.481909.json,1791390295.6262708,1 +v2anneal_merge3_116k_120k,multiblimp_eus,0,lm-eval,vllm,,acc_norm,none,0.6373626373626373,0.029150440533497732,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/361b029fb7_2026-10-07T16-27-19.481909.json,1791390295.6262708,1 +v2anneal_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc,none,0.9408560311284047,0.004654089886680458,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0fa2ba5bf0_2026-10-07T16-33-38.928373.json,1791390656.13628,1 +v2anneal_merge3_116k_120k,multiblimp_fin,0,lm-eval,vllm,,acc_norm,none,0.9334630350194553,0.0049169750402861916,2570,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0fa2ba5bf0_2026-10-07T16-33-38.928373.json,1791390656.13628,1 +v2anneal_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc,none,0.9897959183673469,0.001991339548190257,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/66c31d0f3a_2026-10-07T16-15-38.915790.json,1791389567.0203469,1 +v2anneal_merge3_116k_120k,multiblimp_fra,0,lm-eval,vllm,,acc_norm,none,0.9850863422291993,0.00240167790635628,2548,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/66c31d0f3a_2026-10-07T16-15-38.915790.json,1791389567.0203469,1 +v2anneal_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc,none,0.8571428571428571,0.06734350297014738,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/99d634799e_2026-10-07T16-08-56.431411.json,1791389197.171411,1 +v2anneal_merge3_116k_120k,multiblimp_gle,0,lm-eval,vllm,,acc_norm,none,0.8214285714285714,0.07370704611510599,28,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/99d634799e_2026-10-07T16-08-56.431411.json,1791389197.171411,1 +v2anneal_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc,none,0.9681274900398407,0.006405683674396879,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/db1c350370_2026-10-07T16-27-11.147049.json,1791390287.1375794,1 +v2anneal_merge3_116k_120k,multiblimp_glg,0,lm-eval,vllm,,acc_norm,none,0.953519256308101,0.007677014268718695,753,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/db1c350370_2026-10-07T16-27-11.147049.json,1791390287.1375794,1 +v2anneal_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc,none,0.975958612294583,0.002672561941487074,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8faf4685b9_2026-10-07T16-44-31.654947.json,1791391283.481442,1 +v2anneal_merge3_116k_120k,multiblimp_hbs,0,lm-eval,vllm,,acc_norm,none,0.9762629336579428,0.0026560071211422977,3286,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8faf4685b9_2026-10-07T16-44-31.654947.json,1791391283.481442,1 +v2anneal_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc,none,0.9810650887573964,0.004691474113624961,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e0ed3ed7a6_2026-10-07T16-21-28.546010.json,1791389929.8194585,1 +v2anneal_merge3_116k_120k,multiblimp_hun,0,lm-eval,vllm,,acc_norm,none,0.9810650887573964,0.004691474113624961,845,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e0ed3ed7a6_2026-10-07T16-21-28.546010.json,1791389929.8194585,1 +v2anneal_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc,none,0.97036772581221,0.003204583910713443,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/11901499eb_2026-10-07T16-35-55.054630.json,1791390777.9175029,1 +v2anneal_merge3_116k_120k,multiblimp_isl,0,lm-eval,vllm,,acc_norm,none,0.9614423420207069,0.003638630285386294,2801,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/11901499eb_2026-10-07T16-35-55.054630.json,1791390777.9175029,1 +v2anneal_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc,none,0.9616538846282094,0.0035071494123521,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/67224cdd90_2026-10-07T16-27-54.477651.json,1791390299.824442,1 +v2anneal_merge3_116k_120k,multiblimp_ita,0,lm-eval,vllm,,acc_norm,none,0.9519839946648883,0.0039047391095862853,2999,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/67224cdd90_2026-10-07T16-27-54.477651.json,1791390299.824442,1 +v2anneal_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc,none,0.9656862745098039,0.012776266045095947,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/61033c79de_2026-10-07T16-07-07.053566.json,1791389070.3305316,1 +v2anneal_merge3_116k_120k,multiblimp_kat,0,lm-eval,vllm,,acc_norm,none,0.9264705882352942,0.0183188558500897,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/61033c79de_2026-10-07T16-07-07.053566.json,1791389070.3305316,1 +v2anneal_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc,none,0.9574538258575198,0.0036660316320950635,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6324a73cb1_2026-10-07T16-34-04.618516.json,1791390656.6684697,1 +v2anneal_merge3_116k_120k,multiblimp_lav,0,lm-eval,vllm,,acc_norm,none,0.9548153034300791,0.0037727880034494773,3032,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6324a73cb1_2026-10-07T16-34-04.618516.json,1791390656.6684697,1 +v2anneal_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc,none,0.9822033898305085,0.003850458575728139,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/314c697acd_2026-10-07T16-17-25.153796.json,1791389691.15003,1 +v2anneal_merge3_116k_120k,multiblimp_lit,0,lm-eval,vllm,,acc_norm,none,0.9779661016949153,0.004275143220925853,1180,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/314c697acd_2026-10-07T16-17-25.153796.json,1791389691.15003,1 +v2anneal_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc,none,1.0,0.0,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c47b84a450_2026-10-07T16-10-59.868568.json,1791389319.5864933,1 +v2anneal_merge3_116k_120k,multiblimp_mkd,0,lm-eval,vllm,,acc_norm,none,0.9230769230769231,0.043227037457616635,39,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c47b84a450_2026-10-07T16-10-59.868568.json,1791389319.5864933,1 +v2anneal_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc,none,0.954096954096954,0.004335498559520039,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e267572400_2026-10-07T16-27-40.053671.json,1791390296.0052803,1 +v2anneal_merge3_116k_120k,multiblimp_nld,0,lm-eval,vllm,,acc_norm,none,0.9232089232089232,0.005516040103102192,2331,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e267572400_2026-10-07T16-27-40.053671.json,1791390296.0052803,1 +v2anneal_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc,none,0.9578239608801956,0.003514272808600793,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/13c9c69353_2026-10-07T16-37-57.779943.json,1791390907.203793,1 +v2anneal_merge3_116k_120k,multiblimp_pol,0,lm-eval,vllm,,acc_norm,none,0.9358190709046454,0.004285077425970765,3272,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/13c9c69353_2026-10-07T16-37-57.779943.json,1791390907.203793,1 +v2anneal_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc,none,0.9721128608923885,0.002982799755491494,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/372c7a303f_2026-10-07T16-17-51.584760.json,1791389692.0990496,1 +v2anneal_merge3_116k_120k,multiblimp_por,0,lm-eval,vllm,,acc_norm,none,0.9678477690288714,0.0031957504302086034,3048,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/372c7a303f_2026-10-07T16-17-51.584760.json,1791389692.0990496,1 +v2anneal_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc,none,0.9615758754863813,0.004240214793311917,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8a88b7d565_2026-10-07T16-19-42.546982.json,1791389810.5828562,1 +v2anneal_merge3_116k_120k,multiblimp_ron,0,lm-eval,vllm,,acc_norm,none,0.9576848249027238,0.004440720719971039,2056,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8a88b7d565_2026-10-07T16-19-42.546982.json,1791389810.5828562,1 +v2anneal_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc,none,0.9464414957780458,0.0034974477334934685,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7fc06eac41_2026-10-07T16-11-31.169827.json,1791389317.8593216,1 +v2anneal_merge3_116k_120k,multiblimp_slk,0,lm-eval,vllm,,acc_norm,none,0.9457177322074789,0.003519653287669269,4145,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7fc06eac41_2026-10-07T16-11-31.169827.json,1791389317.8593216,1 +v2anneal_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc,none,0.9326343966094134,0.0037440262956893364,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/319026ba76_2026-10-07T16-05-35.776324.json,1791388941.7829647,1 +v2anneal_merge3_116k_120k,multiblimp_slv,0,lm-eval,vllm,,acc_norm,none,0.9203658264554986,0.004043840848250123,4483,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/319026ba76_2026-10-07T16-05-35.776324.json,1791388941.7829647,1 +v2anneal_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc,none,0.9803227075954348,0.0027558167950625756,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cc7550e874_2026-10-07T16-13-36.241018.json,1791389438.2291334,1 +v2anneal_merge3_116k_120k,multiblimp_spa,0,lm-eval,vllm,,acc_norm,none,0.9838646202282566,0.002500002306405631,2541,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cc7550e874_2026-10-07T16-13-36.241018.json,1791389438.2291334,1 +v2anneal_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc,none,0.9465020576131687,0.01446510656878504,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/666e34f8f2_2026-10-07T16-09-01.433522.json,1791389190.9491718,1 +v2anneal_merge3_116k_120k,multiblimp_sqi,0,lm-eval,vllm,,acc_norm,none,0.9012345679012346,0.019178459585449004,243,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/666e34f8f2_2026-10-07T16-09-01.433522.json,1791389190.9491718,1 +v2anneal_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc,none,0.9950248756218906,0.004975124378109453,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2bee6b0c34_2026-10-07T16-39-33.530843.json,1791391027.6696613,1 +v2anneal_merge3_116k_120k,multiblimp_swe,0,lm-eval,vllm,,acc_norm,none,0.9900497512437811,0.007018276606798947,201,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2bee6b0c34_2026-10-07T16-39-33.530843.json,1791391027.6696613,1 +v2anneal_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc,none,0.9075774971297359,0.006941148514175556,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/59475e4dfa_2026-10-07T16-07-07.934055.json,1791389073.8015234,1 +v2anneal_merge3_116k_120k,multiblimp_tur,0,lm-eval,vllm,,acc_norm,none,0.8444316877152698,0.008686472429738563,1742,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/59475e4dfa_2026-10-07T16-07-07.934055.json,1791389073.8015234,1 +v2anneal_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc,none,0.9774052478134111,0.0028374500215760405,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/65a55cdadd_2026-10-07T16-23-38.442875.json,1791390050.318056,1 +v2anneal_merge3_116k_120k,multiblimp_ukr,0,lm-eval,vllm,,acc_norm,none,0.9712099125364432,0.003192751675577377,2744,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/65a55cdadd_2026-10-07T16-23-38.442875.json,1791390050.318056,1 +v2anneal_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc,none,0.342,0.021236147199899316,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8105954d24_2026-10-07T16-39-46.186096.json,1791391025.7499468,1 +v2anneal_merge3_116k_120k,openbookqa,0,lm-eval,vllm,,acc_norm,none,0.44,0.022221331534143057,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8105954d24_2026-10-07T16-39-46.186096.json,1791391025.7499468,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,bleu,none,15.196770433974953,0.27807156038678865,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/52544e38f6_2026-10-07T16-33-26.083724.json,1791390538.5887234,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_bg_to_en,0,lm-eval,vllm,,chrf,none,33.892951942486334,0.30580398858006963,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/52544e38f6_2026-10-07T16-33-26.083724.json,1791390538.5887234,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,bleu,none,24.24842875402057,0.2823375029725785,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/be11d838e6_2026-10-07T16-35-45.726482.json,1791390661.1742299,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_cs_to_en,0,lm-eval,vllm,,chrf,none,42.87696841656858,0.25597806012044155,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/be11d838e6_2026-10-07T16-35-45.726482.json,1791390661.1742299,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,bleu,none,29.883134381265275,0.3269266712203057,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a7664a4a18_2026-10-07T16-09-21.840401.json,1791389073.9006362,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_da_to_en,0,lm-eval,vllm,,chrf,none,48.98873728413902,0.2724443580952611,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a7664a4a18_2026-10-07T16-09-21.840401.json,1791389073.9006362,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,bleu,none,26.588377154976804,0.31783627269631315,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/465fc30442_2026-10-07T16-21-34.367007.json,1791389804.006249,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_de_to_en,0,lm-eval,vllm,,chrf,none,46.597577441894764,0.27724031254617443,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/465fc30442_2026-10-07T16-21-34.367007.json,1791389804.006249,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,bleu,none,28.443753505013994,0.3637655702905105,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a487da7f9c_2026-10-07T16-09-12.293397.json,1791389072.5589285,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_el_to_en,0,lm-eval,vllm,,chrf,none,46.81599540009167,0.3277734308520369,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a487da7f9c_2026-10-07T16-09-12.293397.json,1791389072.5589285,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,bleu,none,12.180578490954241,0.2571450343432463,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e81af2a80e_2026-10-07T16-23-39.958601.json,1791389931.7003655,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_bg,0,lm-eval,vllm,,chrf,none,36.38285342119661,0.3228423913819547,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e81af2a80e_2026-10-07T16-23-39.958601.json,1791389931.7003655,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,bleu,none,17.593944750710424,0.3000978020607259,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c5519b8f33_2026-10-07T16-31-44.311039.json,1791390417.8615055,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_cs,0,lm-eval,vllm,,chrf,none,40.18452247994384,0.24529329635553415,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c5519b8f33_2026-10-07T16-31-44.311039.json,1791390417.8615055,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,bleu,none,29.32018779905226,0.3245123484095381,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8654b891dc_2026-10-07T16-31-44.347574.json,1791390416.7554445,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_da,0,lm-eval,vllm,,chrf,none,51.27667335345008,0.26018857649248045,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8654b891dc_2026-10-07T16-31-44.347574.json,1791390416.7554445,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,bleu,none,22.381733413225906,0.33224928307256923,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1eb499dddc_2026-10-07T16-07-33.923449.json,1791388952.9758797,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_de,0,lm-eval,vllm,,chrf,none,47.03410396764717,0.3059185703140615,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1eb499dddc_2026-10-07T16-07-33.923449.json,1791388952.9758797,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,bleu,none,22.256047725115987,0.3457924964435046,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3e73038c1e_2026-10-07T16-11-52.514378.json,1791389200.1889827,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_el,0,lm-eval,vllm,,chrf,none,43.76868552872952,0.32206570749401264,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3e73038c1e_2026-10-07T16-11-52.514378.json,1791389200.1889827,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,bleu,none,28.202931828100468,0.37816946511199284,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3cc66e47c7_2026-10-07T16-09-27.085177.json,1791389070.4461186,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_es,0,lm-eval,vllm,,chrf,none,49.44629993859823,0.34677132499175917,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3cc66e47c7_2026-10-07T16-09-27.085177.json,1791389070.4461186,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,bleu,none,21.65164005151509,0.3528675965611025,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c4b694147d_2026-10-07T16-46-06.816884.json,1791391282.2144403,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_et,0,lm-eval,vllm,,chrf,none,45.05782347465426,0.2664794252035123,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c4b694147d_2026-10-07T16-46-06.816884.json,1791391282.2144403,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,bleu,none,16.673569899576545,0.3331662540566593,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/11f50fcff0_2026-10-07T16-11-18.824691.json,1791389191.0954363,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_fi,0,lm-eval,vllm,,chrf,none,45.13732628707749,0.24985961539083837,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/11f50fcff0_2026-10-07T16-11-18.824691.json,1791389191.0954363,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,bleu,none,15.574954932739274,0.24355845924775074,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ecd7eeb462_2026-10-07T16-24-03.429350.json,1791389924.7057056,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_fr,0,lm-eval,vllm,,chrf,none,41.675121556608325,0.27797779530353867,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ecd7eeb462_2026-10-07T16-24-03.429350.json,1791389924.7057056,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,bleu,none,25.381364061085886,0.32577502914750794,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9bab0d2138_2026-10-07T16-11-10.675598.json,1791389187.571684,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_hr,0,lm-eval,vllm,,chrf,none,52.869777458339875,0.2584300199520798,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/9bab0d2138_2026-10-07T16-11-10.675598.json,1791389187.571684,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,bleu,none,17.038169631952623,0.27404471974840033,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8e92fd1c8d_2026-10-07T16-15-56.214401.json,1791389449.3822265,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_hu,0,lm-eval,vllm,,chrf,none,40.22727002426839,0.23734122316347003,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8e92fd1c8d_2026-10-07T16-15-56.214401.json,1791389449.3822265,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,bleu,none,27.666478331130737,0.35749738772006756,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b9f0dfba55_2026-10-07T16-29-49.260802.json,1791390290.6674492,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_it,0,lm-eval,vllm,,chrf,none,49.8976499466029,0.2806594116364996,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b9f0dfba55_2026-10-07T16-29-49.260802.json,1791390290.6674492,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,bleu,none,18.41470755488223,0.3096510114689653,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3ba2083620_2026-10-07T16-40-01.067804.json,1791390899.700315,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_lt,0,lm-eval,vllm,,chrf,none,42.86403682704061,0.2357507753042172,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/3ba2083620_2026-10-07T16-40-01.067804.json,1791390899.700315,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,bleu,none,21.237712291274402,0.3299431983188595,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2da19d2501_2026-10-07T16-13-52.050705.json,1791389331.8659248,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_lv,0,lm-eval,vllm,,chrf,none,44.762886102364355,0.24279750940448844,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2da19d2501_2026-10-07T16-13-52.050705.json,1791389331.8659248,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,bleu,none,19.975308393465884,0.27329949228117656,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/355b5351ec_2026-10-07T16-41-59.489259.json,1791391022.710241,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_nl,0,lm-eval,vllm,,chrf,none,46.0876769033409,0.23134871030805285,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/355b5351ec_2026-10-07T16-41-59.489259.json,1791391022.710241,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,bleu,none,30.64597963200245,0.29895427265769703,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/da7286baa3_2026-10-07T16-15-42.905635.json,1791389451.0484438,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_no,0,lm-eval,vllm,,chrf,none,54.016982578380244,0.2879556985479386,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/da7286baa3_2026-10-07T16-15-42.905635.json,1791389451.0484438,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,bleu,none,20.725757225925545,0.34752441435807435,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6ada8edf5b_2026-10-07T16-18-04.769310.json,1791389565.7913716,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_pl,0,lm-eval,vllm,,chrf,none,45.610625009528455,0.27782010528957835,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6ada8edf5b_2026-10-07T16-18-04.769310.json,1791389565.7913716,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,bleu,none,24.465392485692913,0.30706101697890564,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/05e4eb619c_2026-10-07T16-07-30.189837.json,1791388949.711861,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_pt,0,lm-eval,vllm,,chrf,none,50.63536057631629,0.25837227524684625,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/05e4eb619c_2026-10-07T16-07-30.189837.json,1791388949.711861,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,bleu,none,25.82040185480684,0.3501912108828937,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/277caa304d_2026-10-07T16-46-14.120776.json,1791391280.848075,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_ro,0,lm-eval,vllm,,chrf,none,49.4739315372961,0.2922904311614619,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/277caa304d_2026-10-07T16-46-14.120776.json,1791391280.848075,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,bleu,none,24.33410126315305,0.36720656484585623,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0ef0e6da95_2026-10-07T16-46-20.972177.json,1791391276.0528643,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sk,0,lm-eval,vllm,,chrf,none,46.612636746524906,0.24771369278618488,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0ef0e6da95_2026-10-07T16-46-20.972177.json,1791391276.0528643,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,bleu,none,15.873771632085239,0.2775914054950323,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/433df832d8_2026-10-07T16-15-27.309064.json,1791389438.4054177,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sl,0,lm-eval,vllm,,chrf,none,41.96446124693208,0.26018165033695667,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/433df832d8_2026-10-07T16-15-27.309064.json,1791389438.4054177,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,bleu,none,19.696953344996007,0.33750434788167755,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0881977e7d_2026-10-07T16-19-35.687207.json,1791389684.313348,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sr,0,lm-eval,vllm,,chrf,none,40.07176602334704,0.45332317141171746,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0881977e7d_2026-10-07T16-19-35.687207.json,1791389684.313348,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,bleu,none,33.07170580264981,0.34139336205180176,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d499a9e9c0_2026-10-07T16-40-13.573950.json,1791390904.477001,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_sv,0,lm-eval,vllm,,chrf,none,53.0480051992406,0.3185572953152091,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d499a9e9c0_2026-10-07T16-40-13.573950.json,1791390904.477001,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,bleu,none,20.332265452612244,0.35093664635907634,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5e652164dc_2026-10-07T16-13-40.263652.json,1791389324.8506744,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_tr,0,lm-eval,vllm,,chrf,none,48.0348332051478,0.30101049217542686,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5e652164dc_2026-10-07T16-13-40.263652.json,1791389324.8506744,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,bleu,none,16.720403369087798,0.27482636555489953,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/51dcd51bc4_2026-10-07T16-50-24.696695.json,1791391524.3149729,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_en_to_uk,0,lm-eval,vllm,,chrf,none,38.09399724485753,0.25195938768801646,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/51dcd51bc4_2026-10-07T16-50-24.696695.json,1791391524.3149729,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,bleu,none,29.40276820781482,0.3170725885210214,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cfc1dfb28c_2026-10-07T16-25-47.738420.json,1791390054.9464397,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_es_to_en,0,lm-eval,vllm,,chrf,none,47.808793816630654,0.3163726043329584,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cfc1dfb28c_2026-10-07T16-25-47.738420.json,1791390054.9464397,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,bleu,none,28.037127903718147,0.3489899029479749,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1c9847bf2c_2026-10-07T16-29-39.470270.json,1791390292.070453,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_et_to_en,0,lm-eval,vllm,,chrf,none,46.637095976380266,0.26883971625430886,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1c9847bf2c_2026-10-07T16-29-39.470270.json,1791390292.070453,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,bleu,none,23.044622807124295,0.3128089486843088,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/be50f470be_2026-10-07T16-25-47.180130.json,1791390055.2793536,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_fi_to_en,0,lm-eval,vllm,,chrf,none,42.83169577173108,0.2580229112598593,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/be50f470be_2026-10-07T16-25-47.180130.json,1791390055.2793536,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,bleu,none,17.136376333355653,0.2577536998088545,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1ceebdeb40_2026-10-07T16-41-52.073098.json,1791391025.9043846,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_fr_to_en,0,lm-eval,vllm,,chrf,none,35.29929028451559,0.2850006641209921,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1ceebdeb40_2026-10-07T16-41-52.073098.json,1791391025.9043846,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,bleu,none,29.842030772448513,0.39790395684467494,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/faf01d9e8e_2026-10-07T16-46-04.988048.json,1791391283.5761776,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_hr_to_en,0,lm-eval,vllm,,chrf,none,49.35904746083807,0.3307529212711068,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/faf01d9e8e_2026-10-07T16-46-04.988048.json,1791391283.5761776,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,bleu,none,22.405889136448668,0.2869895734373187,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5267decfea_2026-10-07T16-21-32.851085.json,1791389804.09965,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_hu_to_en,0,lm-eval,vllm,,chrf,none,41.02433542195551,0.23427362898219858,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5267decfea_2026-10-07T16-21-32.851085.json,1791389804.09965,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,bleu,none,29.78974292525246,0.3040619110530177,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8379018afc_2026-10-07T16-13-41.786428.json,1791389318.7260869,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_it_to_en,0,lm-eval,vllm,,chrf,none,47.56157604083803,0.26877551222789414,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8379018afc_2026-10-07T16-13-41.786428.json,1791389318.7260869,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,bleu,none,25.901836802805953,0.3432818061034984,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/68af6a15a0_2026-10-07T16-21-37.367192.json,1791389808.925529,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_lt_to_en,0,lm-eval,vllm,,chrf,none,43.788900443977084,0.27771666525882804,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/68af6a15a0_2026-10-07T16-21-37.367192.json,1791389808.925529,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,bleu,none,27.077292648597343,0.3217159214878049,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/67c3ae5244_2026-10-07T16-37-57.800028.json,1791390780.3387392,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_lv_to_en,0,lm-eval,vllm,,chrf,none,45.501213100443536,0.2771582582177536,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/67c3ae5244_2026-10-07T16-37-57.800028.json,1791390780.3387392,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,bleu,none,22.786767518456287,0.2785288447552733,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5a8877a260_2026-10-07T16-48-04.216433.json,1791391404.542034,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_nl_to_en,0,lm-eval,vllm,,chrf,none,41.85744874973823,0.23840167561864795,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5a8877a260_2026-10-07T16-48-04.216433.json,1791391404.542034,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,bleu,none,31.41869485151978,0.2995290846999245,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b6049cb0b8_2026-10-07T16-13-20.978410.json,1791389318.694804,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_no_to_en,0,lm-eval,vllm,,chrf,none,49.9324379155382,0.2604437170654628,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b6049cb0b8_2026-10-07T16-13-20.978410.json,1791389318.694804,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,bleu,none,26.14825566954306,0.3219706075861181,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c013653e34_2026-10-07T16-39-49.998714.json,1791390904.8013241,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_pl_to_en,0,lm-eval,vllm,,chrf,none,45.116696000332105,0.2741447391358271,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c013653e34_2026-10-07T16-39-49.998714.json,1791390904.8013241,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,bleu,none,30.848895221343234,0.3441998372242955,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/286120a518_2026-10-07T16-25-26.593387.json,1791390047.399582,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_pt_to_en,0,lm-eval,vllm,,chrf,none,47.94825685088413,0.3239962074374729,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/286120a518_2026-10-07T16-25-26.593387.json,1791390047.399582,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,bleu,none,31.146146594630064,0.3886902463355134,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/45264adb1a_2026-10-07T16-31-52.055633.json,1791390425.0182197,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_ro_to_en,0,lm-eval,vllm,,chrf,none,48.49346497936537,0.3281451207726818,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/45264adb1a_2026-10-07T16-31-52.055633.json,1791390425.0182197,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,bleu,none,31.26638060102977,0.31421444485119343,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/92b1726918_2026-10-07T16-33-38.749550.json,1791390536.6562166,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_sk_to_en,0,lm-eval,vllm,,chrf,none,49.03587288091944,0.2660645383150898,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/92b1726918_2026-10-07T16-33-38.749550.json,1791390536.6562166,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,bleu,none,20.720509802766813,0.2853961470284609,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/86cd7d75e1_2026-10-07T16-11-17.245799.json,1791389196.1558805,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_sl_to_en,0,lm-eval,vllm,,chrf,none,40.37416672748188,0.250926065927662,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/86cd7d75e1_2026-10-07T16-11-17.245799.json,1791389196.1558805,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,bleu,none,31.136596215178976,0.33925356921233435,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/54c78bad1f_2026-10-07T16-48-07.101120.json,1791391405.7113519,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_sr_to_en,0,lm-eval,vllm,,chrf,none,51.32788535970283,0.25226687906106926,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/54c78bad1f_2026-10-07T16-48-07.101120.json,1791391405.7113519,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,bleu,none,36.421220625402704,0.3193015596574819,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/77e6cf63d3_2026-10-07T16-11-15.436128.json,1791389187.3211632,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_sv_to_en,0,lm-eval,vllm,,chrf,none,53.29663781252146,0.2763462409589042,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/77e6cf63d3_2026-10-07T16-11-15.436128.json,1791389187.3211632,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,bleu,none,27.806412576434752,0.27757694580766634,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d8d12275aa_2026-10-07T16-19-58.556930.json,1791389693.2971852,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_tr_to_en,0,lm-eval,vllm,,chrf,none,47.2613575632949,0.25642194321413736,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d8d12275aa_2026-10-07T16-19-58.556930.json,1791389693.2971852,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,bleu,none,22.543843037839654,0.3237900813182856,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c8c62e6b54_2026-10-07T16-33-53.895300.json,1791390537.4661376,1 +v2anneal_merge3_116k_120k,opensubtitles_multi40_uk_to_en,0,lm-eval,vllm,,chrf,none,41.032225004454105,0.2901252771719469,6005,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c8c62e6b54_2026-10-07T16-33-53.895300.json,1791390537.4661376,1 +v2anneal_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc,none,0.8106637649619152,0.009140767676614949,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c16a701849_2026-10-07T16-44-08.982266.json,1791391280.9728742,1 +v2anneal_merge3_116k_120k,piqa,0,lm-eval,vllm,,acc_norm,none,0.8188248095756256,0.008986493851714685,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c16a701849_2026-10-07T16-44-08.982266.json,1791391280.9728742,1 +v2anneal_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc,none,0.8269858541893362,0.008825417687866542,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b41cc0abf2_2026-10-07T16-09-45.285970.json,1791389193.3227177,1 +v2anneal_merge3_116k_120k,piqa,10,lm-eval,vllm,,acc_norm,none,0.8373231773667029,0.008611024380872861,1838,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b41cc0abf2_2026-10-07T16-09-45.285970.json,1791389193.3227177,1 +v2anneal_merge3_116k_120k,polymath_de_high,0,lm-eval,vllm,,exact_match,none,0.056,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4359a25aa6_2026-10-07T16-09-40.565042.json,1791389195.6475408,1 +v2anneal_merge3_116k_120k,polymath_de_low,0,lm-eval,vllm,,exact_match,none,0.552,0.04465783896075985,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a8ec4ab0f1_2026-10-07T16-09-38.124612.json,1791389196.134673,1 +v2anneal_merge3_116k_120k,polymath_de_medium,0,lm-eval,vllm,,exact_match,none,0.048,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ef9a8b402d_2026-10-07T16-07-36.665183.json,1791389067.6195755,1 +v2anneal_merge3_116k_120k,polymath_de_top,0,lm-eval,vllm,,exact_match,none,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/421dd28440_2026-10-07T16-44-25.805508.json,1791391277.5188274,1 +v2anneal_merge3_116k_120k,polymath_en_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/833b91e1a3_2026-10-07T16-07-37.676335.json,1791389072.564044,1 +v2anneal_merge3_116k_120k,polymath_en_low,0,lm-eval,vllm,,exact_match,none,0.624,0.04349860954396202,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6229212da2_2026-10-07T16-07-51.130702.json,1791389080.0658317,1 +v2anneal_merge3_116k_120k,polymath_en_medium,0,lm-eval,vllm,,exact_match,none,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e9fc58a831_2026-10-07T16-38-07.520772.json,1791390899.865694,1 +v2anneal_merge3_116k_120k,polymath_en_top,0,lm-eval,vllm,,exact_match,none,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6ea9b2bd95_2026-10-07T16-21-50.424551.json,1791389925.8576605,1 +v2anneal_merge3_116k_120k,polymath_es_high,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c0827a0cf7_2026-10-07T16-07-33.187594.json,1791389071.713119,1 +v2anneal_merge3_116k_120k,polymath_es_low,0,lm-eval,vllm,,exact_match,none,0.552,0.04465783896075985,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/79d39d0f60_2026-10-07T16-27-51.024143.json,1791390290.793137,1 +v2anneal_merge3_116k_120k,polymath_es_medium,0,lm-eval,vllm,,exact_match,none,0.064,0.02197946255470202,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/bbb1173e98_2026-10-07T16-28-17.786245.json,1791390298.1498249,1 +v2anneal_merge3_116k_120k,polymath_es_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/636829eccd_2026-10-07T16-07-32.202808.json,1791389069.9053364,1 +v2anneal_merge3_116k_120k,polymath_fr_high,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/30b77a9a1a_2026-10-07T15-39-01.521321.json,1791387351.0906544,1 +v2anneal_merge3_116k_120k,polymath_fr_low,0,lm-eval,vllm,,exact_match,none,0.52,0.04486539006635796,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8446337be4_2026-10-07T16-44-40.621089.json,1791391288.2048,1 +v2anneal_merge3_116k_120k,polymath_fr_medium,0,lm-eval,vllm,,exact_match,none,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f37d5c0b69_2026-10-07T16-36-16.009928.json,1791390781.8228645,1 +v2anneal_merge3_116k_120k,polymath_fr_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ffecd44773_2026-10-07T16-15-53.835112.json,1791389566.0614731,1 +v2anneal_merge3_116k_120k,polymath_it_high,0,lm-eval,vllm,,exact_match,none,0.016,0.01126799635851396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/779ce17a43_2026-10-07T16-15-55.538223.json,1791389565.2635343,1 +v2anneal_merge3_116k_120k,polymath_it_low,0,lm-eval,vllm,,exact_match,none,0.6,0.043994134506405984,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8bf6ddc62f_2026-10-07T16-27-51.890170.json,1791390289.2221577,1 +v2anneal_merge3_116k_120k,polymath_it_medium,0,lm-eval,vllm,,exact_match,none,0.04,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4d3ee8f61c_2026-10-07T16-44-25.786210.json,1791391280.564794,1 +v2anneal_merge3_116k_120k,polymath_it_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/818a8d7674_2026-10-07T16-13-50.182467.json,1791389440.195466,1 +v2anneal_merge3_116k_120k,polymath_pt_high,0,lm-eval,vllm,,exact_match,none,0.032,0.01580526657835619,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/dd99d4d703_2026-10-07T16-32-01.333343.json,1791390536.2555687,1 +v2anneal_merge3_116k_120k,polymath_pt_low,0,lm-eval,vllm,,exact_match,none,0.624,0.04349860954396202,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/2cd56584b2_2026-10-07T16-46-28.118118.json,1791391403.4467845,1 +v2anneal_merge3_116k_120k,polymath_pt_medium,0,lm-eval,vllm,,exact_match,none,0.048,0.019196773922517764,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0f9faa7d05_2026-10-07T16-07-40.048228.json,1791389071.361959,1 +v2anneal_merge3_116k_120k,polymath_pt_top,0,lm-eval,vllm,,exact_match,none,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/cec1566830_2026-10-07T16-17-50.747174.json,1791389684.4101326,1 +v2anneal_merge3_116k_120k,sib200_als_Latn,0,lm-eval,vllm,,acc,none,0.28921568627450983,0.031822318676475524,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/5aa5d50f08_2026-10-07T16-27-29.580916.json,1791390285.8761349,1 +v2anneal_merge3_116k_120k,sib200_bos_Latn,0,lm-eval,vllm,,acc,none,0.38235294117647056,0.034107853389047135,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f0bbb0e7df_2026-10-07T16-48-01.967016.json,1791391520.7053907,1 +v2anneal_merge3_116k_120k,sib200_bul_Cyrl,0,lm-eval,vllm,,acc,none,0.4166666666666667,0.03460228327239165,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/464676e4ac_2026-10-07T16-15-22.309545.json,1791389565.2491915,1 +v2anneal_merge3_116k_120k,sib200_cat_Latn,0,lm-eval,vllm,,acc,none,0.35294117647058826,0.033540924375915215,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/7d8e381ce5_2026-10-07T15-38-36.873834.json,1791387353.050687,1 +v2anneal_merge3_116k_120k,sib200_ces_Latn,0,lm-eval,vllm,,acc,none,0.4019607843137255,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/89ce89aaba_2026-10-07T16-15-35.857854.json,1791389568.4299421,1 +v2anneal_merge3_116k_120k,sib200_dan_Latn,0,lm-eval,vllm,,acc,none,0.44607843137254904,0.034888454513049706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8c804bcbfe_2026-10-07T16-37-43.534904.json,1791390900.3941238,1 +v2anneal_merge3_116k_120k,sib200_deu_Latn,0,lm-eval,vllm,,acc,none,0.4215686274509804,0.03465868196380755,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d20e9b3873_2026-10-07T16-46-03.145293.json,1791391403.9244337,1 +v2anneal_merge3_116k_120k,sib200_ell_Grek,0,lm-eval,vllm,,acc,none,0.3235294117647059,0.032834720561085606,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/23dafc199b_2026-10-07T16-09-07.622372.json,1791389182.806797,1 +v2anneal_merge3_116k_120k,sib200_eng_Latn,0,lm-eval,vllm,,acc,none,0.4264705882352941,0.034711579079534254,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/540dc91eb7_2026-10-07T16-35-54.782378.json,1791390792.6949868,1 +v2anneal_merge3_116k_120k,sib200_est_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/df06c9790b_2026-10-07T16-11-31.630105.json,1791389327.065042,1 +v2anneal_merge3_116k_120k,sib200_eus_Latn,0,lm-eval,vllm,,acc,none,0.35784313725490197,0.033644872860883,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e6a5a03045_2026-10-07T16-05-14.852099.json,1791388949.6791718,1 +v2anneal_merge3_116k_120k,sib200_fin_Latn,0,lm-eval,vllm,,acc,none,0.4117647058823529,0.03454236585380609,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/0a86268f77_2026-10-07T16-17-26.012817.json,1791389682.9385076,1 +v2anneal_merge3_116k_120k,sib200_fra_Latn,0,lm-eval,vllm,,acc,none,0.36764705882352944,0.0338413204567412,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/34a5897b5b_2026-10-07T16-07-17.823292.json,1791389075.4254396,1 +v2anneal_merge3_116k_120k,sib200_gle_Latn,0,lm-eval,vllm,,acc,none,0.4411764705882353,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c3b2c03b29_2026-10-07T16-39-55.587811.json,1791391033.002787,1 +v2anneal_merge3_116k_120k,sib200_glg_Latn,0,lm-eval,vllm,,acc,none,0.39705882352941174,0.034341311647191244,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f56de572d0_2026-10-07T16-13-36.816876.json,1791389454.5543349,1 +v2anneal_merge3_116k_120k,sib200_hrv_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/29c0add3d5_2026-10-07T16-19-26.274792.json,1791389804.6773689,1 +v2anneal_merge3_116k_120k,sib200_hun_Latn,0,lm-eval,vllm,,acc,none,0.3333333333333333,0.033086111132364336,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/af992a83b1_2026-10-07T16-39-52.283811.json,1791391029.9503417,1 +v2anneal_merge3_116k_120k,sib200_isl_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d75d5e052e_2026-10-07T16-39-47.854029.json,1791391023.9923015,1 +v2anneal_merge3_116k_120k,sib200_ita_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6c0d12615a_2026-10-07T16-39-53.067049.json,1791391025.8380866,1 +v2anneal_merge3_116k_120k,sib200_kat_Geor,0,lm-eval,vllm,,acc,none,0.5,0.03509312031717982,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/df7c926804_2026-10-07T15-38-30.399099.json,1791387346.335142,1 +v2anneal_merge3_116k_120k,sib200_lit_Latn,0,lm-eval,vllm,,acc,none,0.38235294117647056,0.034107853389047135,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1a04c60f4a_2026-10-07T16-27-28.880125.json,1791390287.470364,1 +v2anneal_merge3_116k_120k,sib200_lvs_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c40e95a169_2026-10-07T16-31-33.048861.json,1791390531.2048228,1 +v2anneal_merge3_116k_120k,sib200_mkd_Cyrl,0,lm-eval,vllm,,acc,none,0.3382352941176471,0.03320574612945435,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/bdb26f7df3_2026-10-07T16-43-57.944500.json,1791391280.7854724,1 +v2anneal_merge3_116k_120k,sib200_mlt_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/40d10ef97b_2026-10-07T16-11-29.131377.json,1791389318.5973594,1 +v2anneal_merge3_116k_120k,sib200_nld_Latn,0,lm-eval,vllm,,acc,none,0.4019607843137255,0.03441190023482469,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/74b9728099_2026-10-07T16-05-07.811914.json,1791388948.3587873,1 +v2anneal_merge3_116k_120k,sib200_nob_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d1c63ad75d_2026-10-07T16-17-46.645044.json,1791389691.2440019,1 +v2anneal_merge3_116k_120k,sib200_pol_Latn,0,lm-eval,vllm,,acc,none,0.37254901960784315,0.03393388584958406,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1d588a94ca_2026-10-07T16-07-09.182947.json,1791389068.9638839,1 +v2anneal_merge3_116k_120k,sib200_por_Latn,0,lm-eval,vllm,,acc,none,0.43137254901960786,0.034760990605016404,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/a37f4f4fed_2026-10-07T16-29-35.891458.json,1791390416.6134522,1 +v2anneal_merge3_116k_120k,sib200_ron_Latn,0,lm-eval,vllm,,acc,none,0.37745098039215685,0.03402272044340706,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/ef9e97d78d_2026-10-07T16-13-11.613766.json,1791389436.1000884,1 +v2anneal_merge3_116k_120k,sib200_slk_Latn,0,lm-eval,vllm,,acc,none,0.37254901960784315,0.03393388584958406,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/d489d25edc_2026-10-07T16-27-24.321209.json,1791390286.3506413,1 +v2anneal_merge3_116k_120k,sib200_slv_Latn,0,lm-eval,vllm,,acc,none,0.39215686274509803,0.034267123492472726,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/6a90b61b08_2026-10-07T16-09-02.868506.json,1791389181.1746037,1 +v2anneal_merge3_116k_120k,sib200_spa_Latn,0,lm-eval,vllm,,acc,none,0.39705882352941174,0.034341311647191244,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1c926e202e_2026-10-07T16-13-26.017471.json,1791389438.121189,1 +v2anneal_merge3_116k_120k,sib200_srp_Cyrl,0,lm-eval,vllm,,acc,none,0.37254901960784315,0.03393388584958406,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1e295eac5a_2026-10-07T16-09-13.011334.json,1791389188.72942,1 +v2anneal_merge3_116k_120k,sib200_swe_Latn,0,lm-eval,vllm,,acc,none,0.3872549019607843,0.0341893123383334,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4a95a895b2_2026-10-07T16-27-36.684408.json,1791390300.0942457,1 +v2anneal_merge3_116k_120k,sib200_tur_Latn,0,lm-eval,vllm,,acc,none,0.4411764705882353,0.034849415144292274,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/af01b33f19_2026-10-07T16-13-29.060716.json,1791389444.621046,1 +v2anneal_merge3_116k_120k,sib200_ukr_Cyrl,0,lm-eval,vllm,,acc,none,0.38235294117647056,0.034107853389047135,204,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/29584154f6_2026-10-07T16-27-28.929629.json,1791390286.418805,1 +v2anneal_merge3_116k_120k,social_iqa,0,lm-eval,vllm,,acc,none,0.5286591606960082,0.011295469697754182,1954,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c724997eb3_2026-10-07T16-09-21.544406.json,1791389182.9593718,1 +v2anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_exact,none,80.24628879892038,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b076e331af_2026-10-07T16-44-18.390773.json,1791389444.5182116,1 +v2anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,HasAns_f1,none,86.54875602540538,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b076e331af_2026-10-07T16-44-18.390773.json,1791389444.5182116,1 +v2anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_exact,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b076e331af_2026-10-07T16-44-18.390773.json,1791389444.5182116,1 +v2anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,NoAns_f1,none,0.0,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b076e331af_2026-10-07T16-44-18.390773.json,1791389444.5182116,1 +v2anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_exact,none,58.54459698475533,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b076e331af_2026-10-07T16-44-18.390773.json,1791389444.5182116,1 +v2anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,best_f1,none,59.83598776519975,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b076e331af_2026-10-07T16-44-18.390773.json,1791389444.5182116,1 +v2anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,exact,none,40.065695274993686,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b076e331af_2026-10-07T16-44-18.390773.json,1791389444.5182116,1 +v2anneal_merge3_116k_120k,squadv2,10,lm-eval,vllm,,f1,none,43.212416888621505,,11873,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/b076e331af_2026-10-07T16-44-18.390773.json,1791389444.5182116,1 +v2anneal_merge3_116k_120k,winogrande,0,lm-eval,vllm,,acc,none,0.7119179163378059,0.012727884724248026,1267,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/e15f7bc836_2026-10-07T16-27-33.348077.json,1791390290.854863,1 +v2anneal_merge3_116k_120k,wsc273,0,lm-eval,vllm,,acc,none,0.8461538461538461,0.02187678688440466,273,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/491ca9b4ec_2026-10-07T16-07-18.389799.json,1791389076.1148748,1 +v2anneal_merge3_116k_120k,xcopa:et,0,lighteval,hf/accelerate,,acc,none,0.648,0.02138004238594605,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/bce0a182a3/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-48-37.926835.json,1791391718.2845857,1 +v2anneal_merge3_116k_120k,xcopa:it,0,lighteval,hf/accelerate,,acc,none,0.678,0.02091666833001988,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/8bc208ca35/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-54-33.856922.json,1791392073.9407315,1 +v2anneal_merge3_116k_120k,xcopa:tr,0,lighteval,hf/accelerate,,acc,none,0.648,0.021380042385946058,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/lighteval/2026-10-07-17-31-12/results/14685a0973/results/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/views/plain/v2anneal_merge3_116k_120k/results_2026-10-07T16-48-36.820002.json,1791391716.9044724,1 +v2anneal_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc,none,0.468,0.015786868759359002,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c5d74e3f3a_2026-10-07T16-35-48.076657.json,1791390783.1592069,1 +v2anneal_merge3_116k_120k,xcsqa_deu_Latn,0,lm-eval,vllm,,acc_norm,none,0.442,0.015712507211864152,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/c5d74e3f3a_2026-10-07T16-35-48.076657.json,1791390783.1592069,1 +v2anneal_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc,none,0.642,0.015167928865407633,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/535d456ac6_2026-10-07T16-11-27.392515.json,1791389313.787601,1 +v2anneal_merge3_116k_120k,xcsqa_eng_Latn,0,lm-eval,vllm,,acc_norm,none,0.616,0.015387682761896958,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/535d456ac6_2026-10-07T16-11-27.392515.json,1791389313.787601,1 +v2anneal_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc,none,0.465,0.015780495050030086,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f2db606fa7_2026-10-07T16-17-35.372008.json,1791389690.7525642,1 +v2anneal_merge3_116k_120k,xcsqa_fra_Latn,0,lm-eval,vllm,,acc_norm,none,0.432,0.015672320237336324,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/f2db606fa7_2026-10-07T16-17-35.372008.json,1791389690.7525642,1 +v2anneal_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc,none,0.487,0.015813952101896636,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4926068696_2026-10-07T15-38-43.557049.json,1791387354.9998908,1 +v2anneal_merge3_116k_120k,xcsqa_ita_Latn,0,lm-eval,vllm,,acc_norm,none,0.432,0.015672320237336324,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/4926068696_2026-10-07T15-38-43.557049.json,1791387354.9998908,1 +v2anneal_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc,none,0.46,0.015768596914394403,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/bdcce77ba8_2026-10-07T16-44-06.991860.json,1791391282.2804723,1 +v2anneal_merge3_116k_120k,xcsqa_nld_Latn,0,lm-eval,vllm,,acc_norm,none,0.438,0.01569721001969466,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/bdcce77ba8_2026-10-07T16-44-06.991860.json,1791391282.2804723,1 +v2anneal_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc,none,0.392,0.015445859463771338,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8ed2f8ba76_2026-10-07T16-07-15.953833.json,1791389070.759058,1 +v2anneal_merge3_116k_120k,xcsqa_pol_Latn,0,lm-eval,vllm,,acc_norm,none,0.374,0.015308767369006505,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/8ed2f8ba76_2026-10-07T16-07-15.953833.json,1791389070.759058,1 +v2anneal_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc,none,0.459,0.015766025737882314,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/080233c6d6_2026-10-07T16-13-24.465479.json,1791389436.4405377,1 +v2anneal_merge3_116k_120k,xcsqa_por_Latn,0,lm-eval,vllm,,acc_norm,none,0.437,0.015693223928730425,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/080233c6d6_2026-10-07T16-13-24.465479.json,1791389436.4405377,1 +v2anneal_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc,none,0.462,0.015773547629015002,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1d5bb7f45c_2026-10-07T16-13-51.837547.json,1791389455.867385,1 +v2anneal_merge3_116k_120k,xcsqa_spa_Latn,0,lm-eval,vllm,,acc_norm,none,0.405,0.01553113699045296,1000,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/vllm/2026-10-07-17-31-11/results/1d5bb7f45c_2026-10-07T16-13-51.837547.json,1791389455.867385,1 +v2anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@1,all,0.19479166666666667,0.060076641763137845,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/8f0abded03_2026-10-08T22-27-48.205383.json,1791497332.85076,1 +v2anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@16,all,0.42918469080871746,0.08708505434841313,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/8f0abded03_2026-10-08T22-27-48.205383.json,1791497332.85076,1 +v2anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@32,all,0.4666666666666667,0.09264111117062016,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/8f0abded03_2026-10-08T22-27-48.205383.json,1791497332.85076,1 +v2anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,pass@4,all,0.3034065628476084,0.07274295630528554,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/8f0abded03_2026-10-08T22-27-48.205383.json,1791497332.85076,1 +v2anneal_merge3_116k_120k,aime24_cot,0,lm-eval,vllm,,think_closed,all,0.2,0.060466190562573276,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/8f0abded03_2026-10-08T22-27-48.205383.json,1791497332.85076,1 +v2anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@1,all,0.20520833333333333,0.06629436497972609,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2d4c925f2e_2026-10-08T22-28-01.052836.json,1791497346.2996244,1 +v2anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@16,all,0.3445075849172188,0.08560267078186688,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2d4c925f2e_2026-10-08T22-28-01.052836.json,1791497346.2996244,1 +v2anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@32,all,0.36666666666666664,0.08948554539839963,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2d4c925f2e_2026-10-08T22-28-01.052836.json,1791497346.2996244,1 +v2anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,pass@4,all,0.2798275862068965,0.07643696448830757,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2d4c925f2e_2026-10-08T22-28-01.052836.json,1791497346.2996244,1 +v2anneal_merge3_116k_120k,aime25_cot,0,lm-eval,vllm,,think_closed,all,0.234375,0.06885359879867381,30,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2d4c925f2e_2026-10-08T22-28-01.052836.json,1791497346.2996244,1 +v2anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@1,all,0.55234375,0.061920262962495164,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2ec5762256_2026-10-08T22-28-06.259048.json,1791497342.40486,1 +v2anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@16,all,0.878765603050201,0.0488562207886562,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2ec5762256_2026-10-08T22-28-06.259048.json,1791497342.40486,1 +v2anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@32,all,0.9,0.048038446141526144,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2ec5762256_2026-10-08T22-28-06.259048.json,1791497342.40486,1 +v2anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,pass@4,all,0.7476154060066741,0.053948245368481224,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2ec5762256_2026-10-08T22-28-06.259048.json,1791497342.40486,1 +v2anneal_merge3_116k_120k,amc23_cot,0,lm-eval,vllm,,think_closed,all,0.5203125,0.06615466577412282,40,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2ec5762256_2026-10-08T22-28-06.259048.json,1791497342.40486,1 +v2anneal_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,pass@1,all,0.42992424242424243,0.02718414884843677,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/9005c277db_2026-10-08T22-35-01.295759.json,1791497332.454204,1 +v2anneal_merge3_116k_120k,gpqa_diamond_cot,0,lm-eval,vllm,,think_closed,all,0.32386363636363635,0.027919041604701492,198,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/9005c277db_2026-10-08T22-35-01.295759.json,1791497332.454204,1 +v2anneal_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@1,all,0.6661585365853658,0.030906475540935455,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/3a0481ce1a_2026-10-08T22-13-52.380298.json,1791497335.3465168,1 +v2anneal_merge3_116k_120k,humaneval_cont,0,lm-eval,vllm,,pass@16,all,0.8328371021971319,0.028971716564834226,164,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/3a0481ce1a_2026-10-08T22-13-52.380298.json,1791497335.3465168,1 +v2anneal_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@1,all,0.3282766990291262,0.018632872925557372,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/6cffe87ebc_2026-10-08T22-42-44.579853.json,1791497334.1008945,1 +v2anneal_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,pass@4,all,0.4077669902912621,0.021675582557844252,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/6cffe87ebc_2026-10-08T22-42-44.579853.json,1791497334.1008945,1 +v2anneal_merge3_116k_120k,jeebench_cot,0,lm-eval,vllm,,think_closed,all,0.3825242718446602,0.019389429520539358,515,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/6cffe87ebc_2026-10-08T22-42-44.579853.json,1791497334.1008945,1 +v2anneal_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@1,all,0.17416829745596868,0.015609463569496386,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/9e4d3c0fef_2026-10-08T22-17-48.692267.json,1791497333.1004224,1 +v2anneal_merge3_116k_120k,livecodebench_cont,0,lm-eval,vllm,,pass@4,all,0.21218898518311435,0.01804474500157028,511,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/9e4d3c0fef_2026-10-08T22-17-48.692267.json,1791497333.1004224,1 +v2anneal_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@1,all,0.7435,0.018462047405116734,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/5dcf820f9f_2026-10-08T22-30-12.149225.json,1791497338.18097,1 +v2anneal_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,pass@4,all,0.792,0.01816954222122996,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/5dcf820f9f_2026-10-08T22-30-12.149225.json,1791497338.18097,1 +v2anneal_merge3_116k_120k,math500_cot,0,lm-eval,vllm,,think_closed,all,0.7785,0.017312566242466756,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/5dcf820f9f_2026-10-08T22-30-12.149225.json,1791497338.18097,1 +v2anneal_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@1,all,0.6131875,0.0192966365281647,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/bdc98d21c7_2026-10-08T22-15-36.560020.json,1791497337.9957225,1 +v2anneal_merge3_116k_120k,mbpp_cont,3,lm-eval,vllm,,pass@16,all,0.7521479299366263,0.01901673338566924,500,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/bdc98d21c7_2026-10-08T22-15-36.560020.json,1791497337.9957225,1 +v2anneal_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@1,all,0.086,0.02360699732241788,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2cbe150260_2026-10-08T22-21-11.964000.json,1791497338.0384197,1 +v2anneal_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,pass@4,all,0.112,0.028320743565962956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2cbe150260_2026-10-08T22-21-11.964000.json,1791497338.0384197,1 +v2anneal_merge3_116k_120k,polymath_de_high_cot,0,lm-eval,vllm,,think_closed,all,0.088,0.02363294583906666,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2cbe150260_2026-10-08T22-21-11.964000.json,1791497338.0384197,1 +v2anneal_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@1,all,0.774,0.0332905101270036,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b07d2ef530_2026-10-08T22-14-36.270678.json,1791497331.5523767,1 +v2anneal_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,pass@4,all,0.856,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b07d2ef530_2026-10-08T22-14-36.270678.json,1791497331.5523767,1 +v2anneal_merge3_116k_120k,polymath_de_low_cot,0,lm-eval,vllm,,think_closed,all,0.946,0.016700395977534532,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b07d2ef530_2026-10-08T22-14-36.270678.json,1791497331.5523767,1 +v2anneal_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@1,all,0.232,0.037906506378278276,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/bcaf9cca28_2026-10-08T22-20-46.998737.json,1791497341.6480737,1 +v2anneal_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,pass@4,all,0.232,0.037906506378278276,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/bcaf9cca28_2026-10-08T22-20-46.998737.json,1791497341.6480737,1 +v2anneal_merge3_116k_120k,polymath_de_medium_cot,0,lm-eval,vllm,,think_closed,all,0.272,0.03996127157394334,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/bcaf9cca28_2026-10-08T22-20-46.998737.json,1791497341.6480737,1 +v2anneal_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b89c5407f0_2026-10-08T22-21-06.134625.json,1791497336.82878,1 +v2anneal_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b89c5407f0_2026-10-08T22-21-06.134625.json,1791497336.82878,1 +v2anneal_merge3_116k_120k,polymath_de_top_cot,0,lm-eval,vllm,,think_closed,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b89c5407f0_2026-10-08T22-21-06.134625.json,1791497336.82878,1 +v2anneal_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@1,all,0.078,0.02279218881476156,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/34cddfb150_2026-10-08T22-21-04.372461.json,1791497334.613551,1 +v2anneal_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,pass@4,all,0.096,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/34cddfb150_2026-10-08T22-21-04.372461.json,1791497334.613551,1 +v2anneal_merge3_116k_120k,polymath_en_high_cot,0,lm-eval,vllm,,think_closed,all,0.086,0.02343556712459958,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/34cddfb150_2026-10-08T22-21-04.372461.json,1791497334.613551,1 +v2anneal_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@1,all,0.872,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/c4e432f489_2026-10-08T22-15-05.012035.json,1791497341.6375098,1 +v2anneal_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,pass@4,all,0.872,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/c4e432f489_2026-10-08T22-15-05.012035.json,1791497341.6375098,1 +v2anneal_merge3_116k_120k,polymath_en_low_cot,0,lm-eval,vllm,,think_closed,all,0.96,0.017597653802562393,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/c4e432f489_2026-10-08T22-15-05.012035.json,1791497341.6375098,1 +v2anneal_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@1,all,0.272,0.03996127157394334,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/50910ab6ce_2026-10-08T22-20-35.695563.json,1791497339.6992435,1 +v2anneal_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,pass@4,all,0.272,0.03996127157394334,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/50910ab6ce_2026-10-08T22-20-35.695563.json,1791497339.6992435,1 +v2anneal_merge3_116k_120k,polymath_en_medium_cot,0,lm-eval,vllm,,think_closed,all,0.336,0.04241728193144408,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/50910ab6ce_2026-10-08T22-20-35.695563.json,1791497339.6992435,1 +v2anneal_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@1,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/3daa73d139_2026-10-08T22-21-09.114266.json,1791497341.2062578,1 +v2anneal_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/3daa73d139_2026-10-08T22-21-09.114266.json,1791497341.2062578,1 +v2anneal_merge3_116k_120k,polymath_en_top_cot,0,lm-eval,vllm,,think_closed,all,0.024,0.013744206990818044,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/3daa73d139_2026-10-08T22-21-09.114266.json,1791497341.2062578,1 +v2anneal_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@1,all,0.102,0.025095944923690428,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2badf67981_2026-10-08T22-21-01.943281.json,1791497336.8442476,1 +v2anneal_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,pass@4,all,0.144,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2badf67981_2026-10-08T22-21-01.943281.json,1791497336.8442476,1 +v2anneal_merge3_116k_120k,polymath_es_high_cot,0,lm-eval,vllm,,think_closed,all,0.108,0.025611237452941776,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/2badf67981_2026-10-08T22-21-01.943281.json,1791497336.8442476,1 +v2anneal_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@1,all,0.792,0.028783956104612478,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/adae40ab4e_2026-10-08T22-14-57.801171.json,1791497330.0743961,1 +v2anneal_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,pass@4,all,0.944,0.020647580503418826,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/adae40ab4e_2026-10-08T22-14-57.801171.json,1791497330.0743961,1 +v2anneal_merge3_116k_120k,polymath_es_low_cot,0,lm-eval,vllm,,think_closed,all,0.946,0.016700395977534532,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/adae40ab4e_2026-10-08T22-14-57.801171.json,1791497330.0743961,1 +v2anneal_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@1,all,0.204,0.03316430261202451,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/d865bacc1b_2026-10-08T22-20-57.075442.json,1791497336.8503153,1 +v2anneal_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,pass@4,all,0.256,0.039191835884530846,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/d865bacc1b_2026-10-08T22-20-57.075442.json,1791497336.8503153,1 +v2anneal_merge3_116k_120k,polymath_es_medium_cot,0,lm-eval,vllm,,think_closed,all,0.252,0.03529781131842267,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/d865bacc1b_2026-10-08T22-20-57.075442.json,1791497336.8503153,1 +v2anneal_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@1,all,0.002,0.002,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/ae34c81665_2026-10-08T22-21-08.657464.json,1791497339.7460709,1 +v2anneal_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/ae34c81665_2026-10-08T22-21-08.657464.json,1791497339.7460709,1 +v2anneal_merge3_116k_120k,polymath_es_top_cot,0,lm-eval,vllm,,think_closed,all,0.008,0.004865944857356966,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/ae34c81665_2026-10-08T22-21-08.657464.json,1791497339.7460709,1 +v2anneal_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@1,all,0.07,0.02210677899241214,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/3ccd828e05_2026-10-08T22-21-03.867582.json,1791497332.570816,1 +v2anneal_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,pass@4,all,0.08,0.024362848501289298,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/3ccd828e05_2026-10-08T22-21-03.867582.json,1791497332.570816,1 +v2anneal_merge3_116k_120k,polymath_fr_high_cot,0,lm-eval,vllm,,think_closed,all,0.08,0.022824717784355707,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/3ccd828e05_2026-10-08T22-21-03.867582.json,1791497332.570816,1 +v2anneal_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@1,all,0.752,0.03293395149826881,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/7362af4042_2026-10-08T22-15-15.962772.json,1791497334.3313465,1 +v2anneal_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,pass@4,all,0.856,0.031528788687944106,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/7362af4042_2026-10-08T22-15-15.962772.json,1791497334.3313465,1 +v2anneal_merge3_116k_120k,polymath_fr_low_cot,0,lm-eval,vllm,,think_closed,all,0.924,0.021293645879433366,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/7362af4042_2026-10-08T22-15-15.962772.json,1791497334.3313465,1 +v2anneal_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@1,all,0.226,0.035060316690691956,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/28f3780640_2026-10-08T23-16-11.512211.json,1791500639.1244767,1 +v2anneal_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,pass@4,all,0.28,0.04032129030193482,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/28f3780640_2026-10-08T23-16-11.512211.json,1791500639.1244767,1 +v2anneal_merge3_116k_120k,polymath_fr_medium_cot,0,lm-eval,vllm,,think_closed,all,0.28,0.037524185749047666,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/28f3780640_2026-10-08T23-16-11.512211.json,1791500639.1244767,1 +v2anneal_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@1,all,0.004,0.004,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/21afd2e00e_2026-10-08T22-21-00.715600.json,1791497339.7913601,1 +v2anneal_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,pass@4,all,0.008,0.008,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/21afd2e00e_2026-10-08T22-21-00.715600.json,1791497339.7913601,1 +v2anneal_merge3_116k_120k,polymath_fr_top_cot,0,lm-eval,vllm,,think_closed,all,0.012,0.006257898235236863,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/21afd2e00e_2026-10-08T22-21-00.715600.json,1791497339.7913601,1 +v2anneal_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@1,all,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/8709d4d638_2026-10-08T22-20-55.600807.json,1791497342.0493505,1 +v2anneal_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,pass@4,all,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/8709d4d638_2026-10-08T22-20-55.600807.json,1791497342.0493505,1 +v2anneal_merge3_116k_120k,polymath_it_high_cot,0,lm-eval,vllm,,think_closed,all,0.088,0.025440632980561095,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/8709d4d638_2026-10-08T22-20-55.600807.json,1791497342.0493505,1 +v2anneal_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@1,all,0.812,0.027628876899173396,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b16337e611_2026-10-08T22-14-52.925598.json,1791497334.7750669,1 +v2anneal_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,pass@4,all,0.928,0.02321289963958444,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b16337e611_2026-10-08T22-14-52.925598.json,1791497334.7750669,1 +v2anneal_merge3_116k_120k,polymath_it_low_cot,0,lm-eval,vllm,,think_closed,all,0.968,0.013612138795231451,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/b16337e611_2026-10-08T22-14-52.925598.json,1791497334.7750669,1 +v2anneal_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@1,all,0.218,0.031619716184888555,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/0b7ba2372c_2026-10-08T22-20-47.794280.json,1791497333.319568,1 +v2anneal_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,pass@4,all,0.328,0.04216098180897563,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/0b7ba2372c_2026-10-08T22-20-47.794280.json,1791497333.319568,1 +v2anneal_merge3_116k_120k,polymath_it_medium_cot,0,lm-eval,vllm,,think_closed,all,0.276,0.03393827414016369,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/0b7ba2372c_2026-10-08T22-20-47.794280.json,1791497333.319568,1 +v2anneal_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/4b7fd6c32c_2026-10-08T22-20-51.593900.json,1791497309.0500915,1 +v2anneal_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/4b7fd6c32c_2026-10-08T22-20-51.593900.json,1791497309.0500915,1 +v2anneal_merge3_116k_120k,polymath_it_top_cot,0,lm-eval,vllm,,think_closed,all,0.008,0.004865944857356966,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/4b7fd6c32c_2026-10-08T22-20-51.593900.json,1791497309.0500915,1 +v2anneal_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@1,all,0.08,0.02192362108070477,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/c710889c0e_2026-10-08T22-20-59.383039.json,1791497333.0886676,1 +v2anneal_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,pass@4,all,0.128,0.030002150460559728,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/c710889c0e_2026-10-08T22-20-59.383039.json,1791497333.0886676,1 +v2anneal_merge3_116k_120k,polymath_pt_high_cot,0,lm-eval,vllm,,think_closed,all,0.092,0.02316421043682021,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/c710889c0e_2026-10-08T22-20-59.383039.json,1791497333.0886676,1 +v2anneal_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@1,all,0.75,0.030187585570572634,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/e877096756_2026-10-08T22-14-09.083541.json,1791497332.9408677,1 +v2anneal_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,pass@4,all,0.904,0.026455074517792148,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/e877096756_2026-10-08T22-14-09.083541.json,1791497332.9408677,1 +v2anneal_merge3_116k_120k,polymath_pt_low_cot,0,lm-eval,vllm,,think_closed,all,0.956,0.015570857808843602,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/e877096756_2026-10-08T22-14-09.083541.json,1791497332.9408677,1 +v2anneal_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@1,all,0.212,0.03467080206930657,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/0eb8f199cd_2026-10-08T22-20-52.679758.json,1791497334.3800342,1 +v2anneal_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,pass@4,all,0.248,0.03878143885933063,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/0eb8f199cd_2026-10-08T22-20-52.679758.json,1791497334.3800342,1 +v2anneal_merge3_116k_120k,polymath_pt_medium_cot,0,lm-eval,vllm,,think_closed,all,0.272,0.0365901449802733,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/0eb8f199cd_2026-10-08T22-20-52.679758.json,1791497334.3800342,1 +v2anneal_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@1,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/52f627766d_2026-10-08T22-20-58.831878.json,1791497334.188428,1 +v2anneal_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,pass@4,all,0.0,0.0,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/52f627766d_2026-10-08T22-20-58.831878.json,1791497334.188428,1 +v2anneal_merge3_116k_120k,polymath_pt_top_cot,0,lm-eval,vllm,,think_closed,all,0.016,0.008864572474817402,125,/e/scratch/e-sta-openeurollm/poeppel1/flag-evals/runs/v2anneal_merge3_116k_120k/cot/2026-10-09-00-05-19/results/52f627766d_2026-10-08T22-20-58.831878.json,1791497334.188428,1 From 389476aabc782aaaeff3c74f5274978afd9e8bed Mon Sep 17 00:00:00 2001 From: Jonathan Burdge Date: Fri, 9 Oct 2026 11:35:16 +0300 Subject: [PATCH 2/2] Select corrected CoT and continuation protocols in flagship-1 --- README.md | 2 +- configs/README.md | 2 + configs/evals/aime24_cot.yaml | 22 ++++++++ configs/evals/aime25_cot.yaml | 22 ++++++++ configs/evals/amc23_cot.yaml | 22 ++++++++ configs/evals/gpqa_diamond_cot.yaml | 22 ++++++++ configs/evals/humaneval_cont.yaml | 22 ++++++++ configs/evals/jeebench_cot.yaml | 23 ++++++++ configs/evals/livecodebench_cont.yaml | 22 ++++++++ configs/evals/math500_cot.yaml | 23 ++++++++ configs/evals/mbpp_cont.yaml | 22 ++++++++ configs/evals/polymath.yaml | 2 +- configs/evals/polymath_cot.yaml | 80 +++++++++++++++++++++++++++ configs/sets/flagship-1.yaml | 21 +++---- docs/configuration.md | 19 ++++++- results/README.md | 13 +++-- tests/test_engines.py | 61 ++++++++++++++++++++ tests/test_public_browser.mjs | 32 +++++++++++ 18 files changed, 412 insertions(+), 20 deletions(-) create mode 100644 configs/evals/aime24_cot.yaml create mode 100644 configs/evals/aime25_cot.yaml create mode 100644 configs/evals/amc23_cot.yaml create mode 100644 configs/evals/gpqa_diamond_cot.yaml create mode 100644 configs/evals/humaneval_cont.yaml create mode 100644 configs/evals/jeebench_cot.yaml create mode 100644 configs/evals/livecodebench_cont.yaml create mode 100644 configs/evals/math500_cot.yaml create mode 100644 configs/evals/mbpp_cont.yaml create mode 100644 configs/evals/polymath_cot.yaml diff --git a/README.md b/README.md index 9e427bd..5e1fedc 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,7 @@ The main page opens with **v1annealC_120k_l0fix** as A and **v2anneal_120k** as ## Compare models 1. Select shared models as A and B, or use **Add model CSV** to open your exports. Three labelled synthetic comparisons (perturbed, higher, and lower scores) are supplied for exploring the interface. -2. Choose a **Weighting profile**. **Eval set** starts on **flagship-1** to check the expected evals and apply its language exclusions. Select **Any available** to compare shared measurements without requiring that set. Weights and eval sets are independent. The supplied sets exclude prompted Global PIQA pending scoring validation. +2. Choose a **Weighting profile**. **Eval set** starts on **flagship-1**, using corrected CoT reasoning and code-continuation results with its expected coverage and language exclusions. Missing corrected results show incomplete coverage; original runs remain inspectable. Select **Any available** to compare all recognized shared measurements, which can include both protocols. Weights and eval sets are independent. The supplied sets exclude prompted Global PIQA pending scoring validation. 3. Review **Warnings**, then explore the scores and breakdowns. The global catalogue determines how to interpret each eval: category, scoring field, normalization, and language assignments. **Original** is the startup weighting profile. **Code & math emphasis** gives Code and Math 20% each, with the other category weights adjusted as shown in the [configuration reference](docs/configuration.md#choose-weights-and-expected-coverage). diff --git a/configs/README.md b/configs/README.md index 5c74d16..752e2bc 100644 --- a/configs/README.md +++ b/configs/README.md @@ -11,6 +11,8 @@ Choose the file to edit based on what you want to change: Catalogue `metric`, `metric_filter`, and `shots` are defaults. A named set can override these for a whole eval; omitted values inherit. The dashboard can explicitly relax few-shot matching with warnings. Language exclusions use the catalogue’s assignments, including both translation endpoints. Unknown names are configuration errors. See [set configuration and matching](../docs/configuration.md#strict-and-relaxed-matching). +Distinct evaluation protocols use separate catalogue entries, such as [polymath.yaml](evals/polymath.yaml) and [polymath_cot.yaml](evals/polymath_cot.yaml). The default `flagship-1` set selects the corrected CoT and code-continuation entries, without fallback to original runs. `Any available` can include both; use a named set to choose one protocol per benchmark. + Put repeated language `evidence` and `note` under `language_defaults` in the eval file; individual language entries can override either field. Ordinary entries need only a canonical `language` and `tasks`: scope is inferred from the declared language fields. Keep an explicit `scope: pooled` when a pooled result is assigned to a specific language label. See [shared language metadata](../docs/configuration.md#shared-language-metadata). Each profile or set needs a distinct `name` within its directory. To change a selector's startup choice, edit that directory's `default.txt` to name one YAML file. The catalogue is selected at build time with `--catalogue`, or temporarily loaded in the browser. diff --git a/configs/evals/aime24_cot.yaml b/configs/evals/aime24_cot.yaml new file mode 100644 index 0000000..37591ad --- /dev/null +++ b/configs/evals/aime24_cot.yaml @@ -0,0 +1,22 @@ +name: aime24_cot +category: Reasoning +match: + name: aime24_cot +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0 + max: 1 + basis: not_applicable + note: CoT pass@1; retain the AIME zero floor without a random-integer guessing correction. + sources: + - https://maa.org/maa-invitational-competitions/ +languages: +- language: eng_Latn + tasks: + - aime24_cot + evidence: https://maa.org/maa-invitational-competitions/ + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/aime25_cot.yaml b/configs/evals/aime25_cot.yaml new file mode 100644 index 0000000..b9cd96a --- /dev/null +++ b/configs/evals/aime25_cot.yaml @@ -0,0 +1,22 @@ +name: aime25_cot +category: Reasoning +match: + name: aime25_cot +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0 + max: 1 + basis: not_applicable + note: CoT pass@1; retain the AIME zero floor without a random-integer guessing correction. + sources: + - https://maa.org/maa-invitational-competitions/ +languages: +- language: eng_Latn + tasks: + - aime25_cot + evidence: https://maa.org/maa-invitational-competitions/ + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/amc23_cot.yaml b/configs/evals/amc23_cot.yaml new file mode 100644 index 0000000..455dbe8 --- /dev/null +++ b/configs/evals/amc23_cot.yaml @@ -0,0 +1,22 @@ +name: amc23_cot +category: Reasoning +match: + name: amc23_cot +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0 + max: 1 + basis: not_applicable + note: CoT pass@1; retain the AMC23 zero floor used for open-ended mathematical answers. + sources: + - https://maa.org/student-programs/amc/ +languages: +- language: eng_Latn + tasks: + - amc23_cot + evidence: https://maa.org/student-programs/amc/ + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/gpqa_diamond_cot.yaml b/configs/evals/gpqa_diamond_cot.yaml new file mode 100644 index 0000000..e0f4d92 --- /dev/null +++ b/configs/evals/gpqa_diamond_cot.yaml @@ -0,0 +1,22 @@ +name: gpqa_diamond_cot +category: Knowledge +match: + name: gpqa_diamond_cot +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0.25 + max: 1 + basis: uniform_choice + note: CoT pass@1; retain the GPQA Diamond four-choice uniform-guess baseline of 0.25. + sources: + - https://huggingface.co/datasets/Idavidrein/gpqa +languages: +- language: eng_Latn + tasks: + - gpqa_diamond_cot + evidence: https://huggingface.co/datasets/Idavidrein/gpqa + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/humaneval_cont.yaml b/configs/evals/humaneval_cont.yaml new file mode 100644 index 0000000..a172984 --- /dev/null +++ b/configs/evals/humaneval_cont.yaml @@ -0,0 +1,22 @@ +name: humaneval_cont +category: Code +match: + name: humaneval_cont +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0 + max: 1 + basis: not_applicable + note: Code-continuation pass@1 is graded by executable tests; no random-program baseline is defined. + sources: + - https://github.com/openai/human-eval +languages: +- language: eng_Latn + tasks: + - humaneval_cont + evidence: https://github.com/openai/human-eval + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/jeebench_cot.yaml b/configs/evals/jeebench_cot.yaml new file mode 100644 index 0000000..06fa2a5 --- /dev/null +++ b/configs/evals/jeebench_cot.yaml @@ -0,0 +1,23 @@ +name: jeebench_cot +category: Reasoning +match: + name: jeebench_cot +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0.1055 + max: 1 + note: CoT pass@1; retain the shared JEEBench normalization floor of 0.1055. This is the existing benchmark scoring + convention, based on the paper's mixed-format guessing policy for 515 questions, rather than a measured baseline + for this prompting protocol. + sources: + - https://aclanthology.org/2023.emnlp-main.468.pdf#page=5 +languages: +- language: eng_Latn + tasks: + - jeebench_cot + evidence: https://aclanthology.org/2023.emnlp-main.468.pdf#page=5 + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/livecodebench_cont.yaml b/configs/evals/livecodebench_cont.yaml new file mode 100644 index 0000000..2c12e48 --- /dev/null +++ b/configs/evals/livecodebench_cont.yaml @@ -0,0 +1,22 @@ +name: livecodebench_cont +category: Code +match: + name: livecodebench_cont +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0 + max: 1 + basis: not_applicable + note: Code-continuation pass@1 is graded by executable tests; no random-program baseline is defined. + sources: + - https://github.com/LiveCodeBench/LiveCodeBench +languages: +- language: eng_Latn + tasks: + - livecodebench_cont + evidence: https://github.com/LiveCodeBench/LiveCodeBench + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/math500_cot.yaml b/configs/evals/math500_cot.yaml new file mode 100644 index 0000000..4cf6ccf --- /dev/null +++ b/configs/evals/math500_cot.yaml @@ -0,0 +1,23 @@ +name: math500_cot +category: Math +match: + name: math500_cot +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0 + max: 1 + basis: not_applicable + note: CoT pass@1 for generated mathematical answers; retain the MATH500 zero floor because no common finite answer + space is defined. + sources: + - https://huggingface.co/datasets/HuggingFaceH4/MATH-500 +languages: +- language: eng_Latn + tasks: + - math500_cot + evidence: https://huggingface.co/datasets/HuggingFaceH4/MATH-500 + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/mbpp_cont.yaml b/configs/evals/mbpp_cont.yaml new file mode 100644 index 0000000..ac0e9da --- /dev/null +++ b/configs/evals/mbpp_cont.yaml @@ -0,0 +1,22 @@ +name: mbpp_cont +category: Code +match: + name: mbpp_cont +metric: pass@1 +metric_filter: all +shots: 3 +score: + scale: 1 +normalize: + min: 0 + max: 1 + basis: not_applicable + note: Code-continuation pass@1 is graded by executable tests; no random-program baseline is defined. + sources: + - https://github.com/google-research/google-research/tree/master/mbpp +languages: +- language: eng_Latn + tasks: + - mbpp_cont + evidence: https://github.com/google-research/google-research/tree/master/mbpp + note: English benchmark prompt language; protocol task identifier is recorded in the flag-evals-471 export. diff --git a/configs/evals/polymath.yaml b/configs/evals/polymath.yaml index c1df645..b5ac1a9 100644 --- a/configs/evals/polymath.yaml +++ b/configs/evals/polymath.yaml @@ -1,6 +1,6 @@ name: polymath category: Reasoning -match: {regex: 'polymath_.+'} +match: {regex: 'polymath_.+_(?:low|medium|high|top)'} metric: exact_match metric_filter: none shots: 0 diff --git a/configs/evals/polymath_cot.yaml b/configs/evals/polymath_cot.yaml new file mode 100644 index 0000000..9bcb086 --- /dev/null +++ b/configs/evals/polymath_cot.yaml @@ -0,0 +1,80 @@ +name: polymath_cot +category: Reasoning +match: + regex: polymath_.+_(?:low|medium|high|top)_cot +metric: pass@1 +metric_filter: all +shots: 0 +score: + scale: 1 +normalize: + min: 0 + max: 1 + basis: not_applicable + note: CoT pass@1 for generated mathematical answers; no common finite answer space is defined. + sources: + - https://github.com/QwenLM/PolyMath +aggregation: + components: + - name: low + match: + regex: polymath_.+_low_cot + relative_weight: 1 + - name: medium + match: + regex: polymath_.+_medium_cot + relative_weight: 2 + - name: high + match: + regex: polymath_.+_high_cot + relative_weight: 4 + - name: top + match: + regex: polymath_.+_top_cot + relative_weight: 8 + note: 'PolyMath difficulty-weighted pass@1 combines all four levels within each language: (low + 2 × medium + + 4 × high + 8 × top) / 15. Exported pass@1 values are unweighted per-level scores. Each CoT level is required; + original-protocol rows cannot fill a missing CoT component.' + sources: + - https://qwen-polymath.github.io/#benchmark-score + - https://github.com/QwenLM/PolyMath/blob/main/eval/run_eval.py +language_defaults: + evidence: https://huggingface.co/datasets/Qwen/PolyMath + note: Dataset language follows the underlying PolyMath split; the task suffix identifies the CoT protocol. +languages: +- language: deu_Latn + tasks: + - polymath_de_high_cot + - polymath_de_low_cot + - polymath_de_medium_cot + - polymath_de_top_cot +- language: eng_Latn + tasks: + - polymath_en_high_cot + - polymath_en_low_cot + - polymath_en_medium_cot + - polymath_en_top_cot +- language: spa_Latn + tasks: + - polymath_es_high_cot + - polymath_es_low_cot + - polymath_es_medium_cot + - polymath_es_top_cot +- language: fra_Latn + tasks: + - polymath_fr_high_cot + - polymath_fr_low_cot + - polymath_fr_medium_cot + - polymath_fr_top_cot +- language: ita_Latn + tasks: + - polymath_it_high_cot + - polymath_it_low_cot + - polymath_it_medium_cot + - polymath_it_top_cot +- language: por_Latn + tasks: + - polymath_pt_high_cot + - polymath_pt_low_cot + - polymath_pt_medium_cot + - polymath_pt_top_cot diff --git a/configs/sets/flagship-1.yaml b/configs/sets/flagship-1.yaml index f2d3c05..c7bb911 100644 --- a/configs/sets/flagship-1.yaml +++ b/configs/sets/flagship-1.yaml @@ -3,28 +3,29 @@ name: flagship-1 mode: fixed exclude_languages: [kat_Geor] notes: + - Use corrected CoT reasoning and code-continuation protocols; original-protocol results are excluded without fallback. - Require the catalogue tasks for each listed eval, inheriting its scoring defaults. - Exclude Georgian results because of a vocabulary error. Exclude English X-CSQA to avoid overlap with CommonsenseQA. evals: - name: bigbench_cs_algorithms - - name: HumanEval - - name: LiveCodeBench - - name: mbpp + - name: humaneval_cont + - name: livecodebench_cont + - name: mbpp_cont - name: bigbench_dyck_languages - name: bigbench_operators - name: bigbench_repeat_copy_logic - name: gsm8k - name: mgsm - - name: MATH500 - - name: AIME24 - - name: AIME25 - - name: AMC23 - - name: JEEBench + - name: math500_cot + - name: aime24_cot + - name: aime25_cot + - name: amc23_cot + - name: jeebench_cot - name: agieval_lsat_ar - - name: polymath + - name: polymath_cot - name: arc_challenge - name: arc_easy - - name: GPQADiamond + - name: gpqa_diamond_cot - name: include_base_44 - name: jeopardy - name: mmlu diff --git a/docs/configuration.md b/docs/configuration.md index acc62e5..9460000 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -6,7 +6,7 @@ Quickdash separates four inputs: model results, a weighting profile, an optional | --- | --- | --- | | CSV results | Raw measurements for models A and B | Shared files in `results/`, or browser imports | | Weighting profile | Category weights, English shares, default calculation | `configs/weights/oellm.yaml` | -| Eval set | Optional expected evals and variants | `configs/sets/any-available.yaml` | +| Eval set | Optional expected evals and variants | `configs/sets/flagship-1.yaml` on dashboard startup | | Global catalogue | Match tasks to evals, categories, metrics, normalization and languages | `configs/catalogue.yaml` → `configs/evals/` | ## Choose weights and expected coverage @@ -33,6 +33,19 @@ Both profiles default to the standard calculation and store an English share of **flagship-1** requires the catalogue's known tasks for each listed eval, excluding Georgian throughout the set because of a vocabulary error and English specifically for X-CSQA. Original and translated tasks stay under their existing eval group (for example `arc_challenge`). A missing required result generates a warning even if other languages for that eval are present. The score is labelled **INCOMPLETE** and uses the shared subset with redistributed weights. Excluded tasks are not requirements; present excluded data produces **Not used** warnings and remains inspectable. +The set uses the corrected CoT reasoning and code-continuation protocols from the `flag-evals-471` exports. Each has its own catalogue entry, so the original and corrected runs retain distinct task identities: + +| Original eval | Selected corrected eval | +| --- | --- | +| AIME24, AIME25, AMC23 | `aime24_cot`, `aime25_cot`, `amc23_cot` | +| GPQADiamond, JEEBench, MATH500 | `gpqa_diamond_cot`, `jeebench_cot`, `math500_cot` | +| HumanEval, LiveCodeBench, mbpp | `humaneval_cont`, `livecodebench_cont`, `mbpp_cont` | +| polymath | `polymath_cot` (all four difficulty levels in each of six languages) | + +These entries select `pass@1` with filter `all`, at 0 shots except `mbpp_cont` at 3 shots. Alternate metrics such as `pass@4` and `think_closed` remain raw inspection fields. Category assignments, normalization floors, and PolyMath difficulty weights are retained. The inherited JEEBench floor of 0.1055 is a shared scoring convention, not a newly measured baseline for CoT prompting. + +`flagship-1` excludes the original entries, avoiding duplicate contributions from the same benchmark. Missing corrected results leave coverage incomplete, even when an original run is present; relaxed matching does not substitute a different task or metric. Original entries remain available for custom sets and inspection. **Any available** can include both original and corrected entries as separate evals, so its score answers a different comparison question. + A named set can be concise: ```yaml @@ -83,7 +96,7 @@ The dashboard starts with **Strict matching**. Expected settings are resolved in Relaxed matching never substitutes a different metric or metric filter, or pairs different harnesses/backends. Component groups must still contain every component at one consistent actual shot count. If per-task selection leaves a mixed-shot or incomplete component group, the group is excluded; the engine does not search for a different combination to rescue it. -When a differing shot count actually contributes, the page prominently reports **INCONSISTENT EVALUATION SETTINGS**. Warnings give the eval, model, tasks, expected count, and actual count. Real measurement identities retain their actual settings. Enabling relaxed mode alone does not label a comparison inconsistent if no mismatched measurements contribute. The shipped working expectations are 10 shots for ARC Challenge and PIQA, and 5 for MGSM; their 0-shot translated/global variants need relaxed matching unless the set overrides the expectation. +When a differing shot count actually contributes, the page prominently reports **INCONSISTENT EVALUATION SETTINGS**. Warnings give the eval, model, tasks, expected count, and actual count. Real measurement identities retain their actual settings. Enabling relaxed mode alone does not label a comparison inconsistent if no mismatched measurements contribute. The shipped working expectations are 25 shots for ARC Challenge, 10 for PIQA, and 5 for MGSM; their 0-shot translated/global variants need relaxed matching unless the set overrides the expectation. A weighting profile works with either mode: @@ -298,7 +311,7 @@ aggregation: Each component requires a unique nonempty `name`, a full-task `match` (exact `name` or `regex`, as for eval matching), and a positive finite numeric `relative_weight`. The weight sum must be finite. The list must be nonempty. Optional `note` is text and `sources` is a list of HTTP(S) URLs. Unknown fields are rejected. Multiplying all component weights by the same positive constant leaves the result unchanged. -The supplied PolyMath rule implements the authors' [Difficulty-Weighted Accuracy](https://qwen-polymath.github.io/#benchmark-score): `(low + 2×medium + 4×high + 8×top)/15`. The [oellm-eval template](https://github.com/OpenEuroLLM/oellm-eval/blob/8a4b2412a8e8f7f0d95e3845e2164c792add6a79/oellm/resources/custom_lm_eval_tasks/polymath/_default_template_yaml) emits a mean accuracy for each difficulty split; those input values are not already difficulty-weighted. +Both supplied PolyMath rules use the authors' [Difficulty-Weighted Accuracy](https://qwen-polymath.github.io/#benchmark-score) formula: `(low + 2×medium + 4×high + 8×top)/15`. The original `polymath` entry selects `exact_match` with filter `none`; the [oellm-eval template](https://github.com/OpenEuroLLM/oellm-eval/blob/8a4b2412a8e8f7f0d95e3845e2164c792add6a79/oellm/resources/custom_lm_eval_tasks/polymath/_default_template_yaml) emits a mean accuracy for each difficulty split. The default set selects `polymath_cot`, whose task and component matches end in `_cot`, with metric `pass@1` and filter `all`. Both take unweighted per-level inputs and require all four levels within a language. Original-protocol rows cannot fill missing CoT levels. Calculation order: diff --git a/results/README.md b/results/README.md index e486d80..083e693 100644 --- a/results/README.md +++ b/results/README.md @@ -7,11 +7,14 @@ When this directory contains no CSVs, Pages shows the [sample dataset and synthe The shared files are `flag-evals-471` exports retrieved on 2026-10-09 from `/scratch/project_465002530/poppelko/flag-evals/results/` on LUMI. Each contains 2,123 measurement rows, including 101 rows for 33 `_cot` reasoning and `_cont` -code-continuation tasks. These protocol variants have distinct task identifiers; -their raw rows are available for inspection but are not selected by the shipped -scoring rules. Dedicated catalogue rules are needed before these new metrics can -contribute to composite scores. The exports retain their original metric values, -shot counts, checkpoint labels, and source metadata. +code-continuation tasks. The default `flagship-1` set selects these corrected +protocols using `pass@1`, filter `all`, at 0 shots (3 for `mbpp_cont`). Original +protocol rows remain inspectable under separate catalogue entries but do not +contribute to this set. Missing corrected results produce incomplete coverage; +there is no fallback to original runs. **Any available** can include both +protocols. See the [protocol selection rules](../docs/configuration.md#choose-weights-and-expected-coverage). +The exports retain their original metric values, shot counts, checkpoint labels, +and source metadata. Choose the models shown on first opening the dashboard in [default.yaml](default.yaml): diff --git a/tests/test_engines.py b/tests/test_engines.py index 961534a..13de995 100644 --- a/tests/test_engines.py +++ b/tests/test_engines.py @@ -887,6 +887,67 @@ def test_flagship_exclusions_are_set_policy(self): ) ) + def test_flagship_selects_corrected_protocols_without_legacy_fallback(self): + replacements = { + "AIME24": "aime24_cot", "AIME25": "aime25_cot", "AMC23": "amc23_cot", + "GPQADiamond": "gpqa_diamond_cot", "HumanEval": "humaneval_cont", + "JEEBench": "jeebench_cot", "LiveCodeBench": "livecodebench_cont", + "MATH500": "math500_cot", "mbpp": "mbpp_cont", "polymath": "polymath_cot", + } + config = load_config(catalogue=ROOT / "configs/catalogue.yaml", + weights=ROOT / "configs/weights/oellm.yaml", + eval_set=ROOT / "configs/sets/flagship-1.yaml") + required = {e["name"]: e for e in config["suite"]["evals"]} + self.assertTrue(set(replacements.values()) <= required.keys()) + self.assertFalse(set(replacements) & required.keys()) + definitions = {e["name"]: e for e in config["catalogue"]["evals"]} + for old_name, new_name in replacements.items(): + with self.subTest(eval=new_name): + old = definitions[old_name] + # Scores are invented. Only the protocol selection contract uses shipped rules. + if old_name == "polymath": + old_tasks = [t for g in config["catalogue"]["languages"] for t in g["tasks"] + if re.fullmatch(r"polymath_.+_(low|medium|high|top)", t)] + new_tasks = [t + "_cot" for t in old_tasks] + else: + old_tasks, new_tasks = [old["match"]["name"]], [new_name] + shots = "3" if new_name == "mbpp_cont" else "0" + legacy = [row(t, "1", metric=old["metric"], filter=old["metric_filter"], + n_shot=str(old["shots"])) for t in old_tasks] + corrected = [row(t, ".6", metric="pass@1", filter="all", n_shot=shots) for t in new_tasks] + alternatives = [row(t, "1", metric=metric, filter=filter_, n_shot=shots) + for t in new_tasks for metric, filter_ in + [("pass@4", "all"), ("think_closed", "all"), ("pass@1", "none")]] + subset = {**config, "suite": {**config["suite"], "evals": [required[new_name]]}} + complete = dict(config=subset, rows=legacy + corrected + alternatives) + missing = dict(config=subset, rows=legacy + alternatives) + for outputs in self.both([complete, {**complete, "matching": "relaxed"}]): + for output in outputs: + self.assertNotIn("error", output) + report = output["value"] + measurements = report["models"][0]["measurements"] + included = [m for m in measurements if m["included"]] + self.assertEqual({m["task"] for m in included}, set(new_tasks)) + self.assertEqual(len(included), len(new_tasks)) + self.assertEqual({(m["metric"], m["filter"], m["n_shot"]) for m in included}, + {("pass@1", "all", shots)}) + self.assertTrue(all(not m["included"] for m in measurements if m["task"] in old_tasks)) + self.assertNotIn("missing_suite_data", {d["code"] for d in report["diagnostics"]}) + self.assertAlmostEqual(sum(m["effective_weight"] for m in included), 1) + for outputs in self.both([missing, {**missing, "matching": "relaxed"}]): + for output in outputs: + self.assertNotIn("error", output) + report = output["value"] + self.assertIsNone(report["models"][0]["score"]) + self.assertFalse(any(m["included"] for m in report["models"][0]["measurements"])) + self.assertIn("missing_suite_data", {d["code"] for d in report["diagnostics"]}) + if old_name == "polymath": + incomplete = {**complete, "rows": legacy + [r for r in corrected if not r["task"].endswith("_top_cot")]} + for output in self.both([incomplete])[0]: + self.assertNotIn("error", output) + self.assertIsNone(output["value"]["models"][0]["score"]) + self.assertIn("incomplete_components", {d["code"] for d in output["value"]["diagnostics"]}) + def test_published_sample_across_all_shipped_configs(self): # Discover files so adding a profile or set automatically extends parity coverage. rows = parse_csv((ROOT / "examples/sample-evals.csv").read_text()) diff --git a/tests/test_public_browser.mjs b/tests/test_public_browser.mjs index 57b6c39..5c466ac 100644 --- a/tests/test_public_browser.mjs +++ b/tests/test_public_browser.mjs @@ -347,6 +347,38 @@ try{ await change('#matching','strict'); assert.equal(await evaluate("document.querySelector('#cards').textContent"),strictCards); } + // Named sets select a corrected protocol once and never substitute an older run. + await navigate(pathToFileURL(path.join(empty,'index.html')).href); + const protocolCatalogue={version:1,name:'Protocol fixture',evals:[ + {name:'Original protocol',category:'Reasoning',match:{name:'protocol'},metric:'accuracy_avg',metric_filter:'',shots:0,score:{scale:1}}, + {name:'CoT protocol',category:'Reasoning',match:{name:'protocol_cot'},metric:'pass@1',metric_filter:'all',shots:0,score:{scale:1}}, + ],languages:[{tasks:['protocol','protocol_cot'],scope:'single',language:'eng_Latn'}]}; + await click('[data-view=config]');await upload('#suiteFile',serializeSuite(shotAvailable),'available.yaml'); + await upload('#configFile',serializeCatalogue(protocolCatalogue),'protocols.yaml'); + await upload('#weightsFile',serializeWeightProfile({version:1,name:'Protocol weights',weights:{Reasoning:1}}),'weights.yaml'); + await upload('#suiteFile',serializeSuite({version:1,name:'Corrected protocol',mode:'fixed',evals:[{name:'CoT protocol'}]}),'corrected.yaml'); + const protocolRows=['checkpoint,task,metric,filter,n_shot,harness,backend,value', + 'Protocol A,protocol,accuracy_avg,,0,test,cpu,1','Protocol B,protocol,accuracy_avg,,0,test,cpu,1', + 'Protocol A,protocol_cot,pass@1,all,0,test,cpu,0.6','Protocol B,protocol_cot,pass@1,all,0,test,cpu,0.4', + 'Protocol A,protocol_cot,pass@4,all,0,test,cpu,1','Protocol B,protocol_cot,pass@4,all,0,test,cpu,1', + 'Original only,protocol,accuracy_avg,,0,test,cpu,1']; + await upload('#modelFile',protocolRows.join('\n'),'protocols.csv'); + await change('#modelA','Protocol A');await change('#modelB','Protocol B'); + assert.equal(await evaluate("document.querySelector('#error').textContent"),''); + assert.deepEqual(await evaluate("[...document.querySelectorAll('.score-card strong')].map(e=>e.textContent)"),['60.00','40.00','20.00']); + assert.match(await evaluate("document.querySelector('#coverage').textContent"),/Complete.*1\/1 requirements shared/); + await click('[data-view=warnings]');assert.match(await evaluate("document.querySelector('#view').textContent"),/Not used.*Original protocol/s); + await click('[data-view=config]'); + assert.ok(await evaluate("document.querySelector('[data-eval=\"Original protocol\"]')!==null")); + assert.ok(await evaluate("document.querySelector('[data-eval=\"CoT protocol\"]')!==null")); + await change('#modelB','Original only'); + for(const matching of ['strict','relaxed']){ + await change('#matching',matching); + assert.equal(await evaluate("document.querySelector('#error').textContent"),''); + assert.deepEqual(await evaluate("[...document.querySelectorAll('.score-card strong')].map(e=>e.textContent)"),['—','—','—']); + assert.match(await evaluate("document.querySelector('#coverage').textContent"),/INCOMPLETE.*0\/1 requirements shared/); + await click('[data-view=warnings]');assert.match(await evaluate("document.querySelector('#view').textContent"),/Missing suite data.*CoT protocol.*Original only/s); + } // Real A/B few-shot differences are allowed only through the explicit runtime option. await navigate(pathToFileURL(path.join(empty,'index.html')).href); const expectedShots=structuredClone(fixture);expectedShots.evals[0].shots=5;